Face recognition is a challenge due to facial expression, direction, light, and scale variations. The system requires a suitable algorithm to perform recognition task in order to reduce the system complexity. This paper focuses on a development of a new local feature extraction in frequency domain to reduce dimension of feature space. In the propose method, assemble of DCT coefficients are used to extract important features and reduces the features vector. PCA is performed to further reduce feature dimension by using linear projection of original image. The proposed of assemble low frequency coefficients and features reduction method is able to increase discriminant power in low dimensional feature space. The classification is performed by using the Euclidean distance score between the projection of test and train images. The algorithm is implemented on DSP processor which has the same performance as PC based. The experiment is conducted using ORL standard face databases the best performance achieved by this method is 100%. The execution time to recognize 40 peoples is 0.3313 second when tested using DSP processor. The proposed method has a high degree of recognition accuracy and fast computational time when implemented in embedded platform such as DSP processor.
IRJET- An Efficient VLSI Architecture for 3D-DWT using Lifting SchemeIRJET Journal
This document proposes an efficient VLSI architecture for 3D discrete wavelet transform (DWT) using the lifting scheme. The lifting scheme implementation of DWT has lower area, power consumption and computational complexity compared to convolution-based DWT. The proposed architecture achieves reductions in total area and power compared to existing convolution DWT and discrete cosine transform architectures. It evaluates the performance in terms of area analysis, timing reports, and output matrices after 1D, 2D and 3D DWT using both convolution and lifting schemes. The results show that the lifting scheme provides better compression performance with less area and delay.
Dataset Pre-Processing and Artificial Augmentation, Network Architecture and ...INFOGAIN PUBLICATION
Training a Convolutional Neural Network (CNN) based classifier is dependent on a large number of factors. These factors involve tasks such as aggregation of apt dataset, arriving at a suitable CNN network, processing of the dataset, and selecting the training parameters to arrive at the desired classification results. This review includes pre-processing techniques and dataset augmentation techniques used in various CNN based classification researches. In many classification problems, it is usually observed that the quality of dataset is responsible for proper training of CNN network, and this quality is judged on the basis of variations in data for every class. It is not usual to find such a pre-made dataset due to many natural concerns. Also it is recommended to have a large dataset, which is again not usually made available directly as a dataset. In some cases, the noise present in the dataset may not prove useful for training, while in others, researchers prefer to add noise to certain images to make the network less vulnerable to unwanted variations. Hence, researchers use artificial digital imaging techniques to derive variations in the dataset and clear or add noise. Thus, the presented paper accumulates state-of-the-art works that used the pre-processing and artificial augmentation of dataset before training. The next part to data augmentation is training, which includes proper selection of several parameters and a suitable CNN architecture. This paper also includes such network characteristics, dataset characteristics and training methodologies used in biomedical imaging, vision modules of autonomous driverless cars, and a few general vision based applications.
AN OPTIMIZED BLOCK ESTIMATION BASED IMAGE COMPRESSION AND DECOMPRESSION ALGOR...IAEME Publication
This document presents a new optimized block estimation based image compression and decompression algorithm. The proposed method divides images into blocks and estimates each block from the previous frame using sum of absolute differences to determine the best matching block. It then compresses the luminance channel using JPEG-LS coding and predicts chrominance channels using hierarchical decomposition and directional prediction. Experimental results on test images show the proposed method achieves higher compression rates and lower distortion compared to traditional models that use hierarchical schemes and raster scan prediction.
AN EFFICIENT M-ARY QIM DATA HIDING ALGORITHM FOR THE APPLICATION TO IMAGE ERR...IJNSA Journal
Methods like edge directed interpolation and projection onto convex sets (POCS) that are widely used for image error concealment to produce better image quality are complex in nature and also time consuming. Moreover, those methods are not suitable for real time error concealment where the decoder may not have sufficient computation power or done in online. In this paper, we propose a data-hiding scheme for error concealment of digital image. Edge direction information of a block is extracted in the encoder and is embedded imperceptibly into the host media using quantization index modulation (QIM), thus reduces work load of the decoder. The system performance in term of fidelity and computational load is improved using M-ary data modulation based on near-orthogonal QIM. The decoder extracts the embedded
features (edge information) and those features are then used for recovery of lost data. Experimental results duly support the effectiveness of the proposed scheme.
IRJET- Enhancement of Image using Fuzzy Inference System for Remotely Sen...IRJET Journal
This document discusses using a fuzzy inference system to enhance remotely sensed multi-temporal images. It proposes a spectral resolution enhancement method (SREM) that uses fuzzy logic to increase image contrast and quality. The method involves fuzzifying the original image using triangular membership functions, then applying fuzzy rules to modify membership values. Finally, defuzzification converts the image back from the fuzzy membership plane to the pixel plane, producing an enhanced image with increased contrast. The approach is tested on eight image datasets and statistical analysis shows the fuzzy inference system produces enhanced images that improve the range of applications for remotely sensed data.
An Investigation towards Effectiveness in Image Enhancement Process in MPSoC IJECEIAES
The document discusses image enhancement techniques for use in multiprocessor systems-on-chip (MPSoC). It reviews existing image enhancement methods implemented on FPGA and identifies limitations like low accuracy. The paper proposes using advanced bus architectures like AMBA/AXI in MPSoC to improve communication between memory and input medical images for enhancement, reducing heterogeneity effects. It summarizes various image enhancement algorithms that could be implemented on reconfigurable FPGA hardware for use in MPSoC, including brightness control, contrast stretching, histogram equalization, and edge detection techniques.
Reversible Image Data Hiding with Contrast EnhancementIRJET Journal
This document proposes a reversible image data hiding technique with contrast enhancement. It aims to embed data into a cover image in a reversible manner while also enhancing the contrast of the cover image. The technique first calculates prediction errors of pixel values in the cover image. It then generates a histogram of the prediction errors and selects carriers for data embedding from peaks in the histogram. Binary secret data is embedded into the carriers by dynamically shifting the prediction error histogram. This allows data to be embedded while increasing cover image quality compared to other reversible data hiding methods. The original cover image can be recovered by extracting the embedded data and reversing the histogram shifts. The technique is meant to achieve a higher peak signal-to-noise ratio than the original cover image after data
IRJET- Handwritten Decimal Image Compression using Deep Stacked AutoencoderIRJET Journal
This document proposes using a deep stacked autoencoder neural network for compressing handwritten decimal image data. It involves training multiple autoencoders in sequence to form a deep network that can compress the high-dimensional input images into lower-dimensional encoded representations while minimizing information loss. The autoencoders are trained one layer at a time using scaled conjugate gradient descent. Testing on the MNIST handwritten digits dataset showed the deep stacked autoencoder achieved compression by encoding the 400-dimensional input images down to a 25-dimensional representation while maintaining good reconstruction accuracy, as measured by minimizing the mean squared error at each layer.
IRJET- An Efficient VLSI Architecture for 3D-DWT using Lifting SchemeIRJET Journal
This document proposes an efficient VLSI architecture for 3D discrete wavelet transform (DWT) using the lifting scheme. The lifting scheme implementation of DWT has lower area, power consumption and computational complexity compared to convolution-based DWT. The proposed architecture achieves reductions in total area and power compared to existing convolution DWT and discrete cosine transform architectures. It evaluates the performance in terms of area analysis, timing reports, and output matrices after 1D, 2D and 3D DWT using both convolution and lifting schemes. The results show that the lifting scheme provides better compression performance with less area and delay.
Dataset Pre-Processing and Artificial Augmentation, Network Architecture and ...INFOGAIN PUBLICATION
Training a Convolutional Neural Network (CNN) based classifier is dependent on a large number of factors. These factors involve tasks such as aggregation of apt dataset, arriving at a suitable CNN network, processing of the dataset, and selecting the training parameters to arrive at the desired classification results. This review includes pre-processing techniques and dataset augmentation techniques used in various CNN based classification researches. In many classification problems, it is usually observed that the quality of dataset is responsible for proper training of CNN network, and this quality is judged on the basis of variations in data for every class. It is not usual to find such a pre-made dataset due to many natural concerns. Also it is recommended to have a large dataset, which is again not usually made available directly as a dataset. In some cases, the noise present in the dataset may not prove useful for training, while in others, researchers prefer to add noise to certain images to make the network less vulnerable to unwanted variations. Hence, researchers use artificial digital imaging techniques to derive variations in the dataset and clear or add noise. Thus, the presented paper accumulates state-of-the-art works that used the pre-processing and artificial augmentation of dataset before training. The next part to data augmentation is training, which includes proper selection of several parameters and a suitable CNN architecture. This paper also includes such network characteristics, dataset characteristics and training methodologies used in biomedical imaging, vision modules of autonomous driverless cars, and a few general vision based applications.
AN OPTIMIZED BLOCK ESTIMATION BASED IMAGE COMPRESSION AND DECOMPRESSION ALGOR...IAEME Publication
This document presents a new optimized block estimation based image compression and decompression algorithm. The proposed method divides images into blocks and estimates each block from the previous frame using sum of absolute differences to determine the best matching block. It then compresses the luminance channel using JPEG-LS coding and predicts chrominance channels using hierarchical decomposition and directional prediction. Experimental results on test images show the proposed method achieves higher compression rates and lower distortion compared to traditional models that use hierarchical schemes and raster scan prediction.
AN EFFICIENT M-ARY QIM DATA HIDING ALGORITHM FOR THE APPLICATION TO IMAGE ERR...IJNSA Journal
Methods like edge directed interpolation and projection onto convex sets (POCS) that are widely used for image error concealment to produce better image quality are complex in nature and also time consuming. Moreover, those methods are not suitable for real time error concealment where the decoder may not have sufficient computation power or done in online. In this paper, we propose a data-hiding scheme for error concealment of digital image. Edge direction information of a block is extracted in the encoder and is embedded imperceptibly into the host media using quantization index modulation (QIM), thus reduces work load of the decoder. The system performance in term of fidelity and computational load is improved using M-ary data modulation based on near-orthogonal QIM. The decoder extracts the embedded
features (edge information) and those features are then used for recovery of lost data. Experimental results duly support the effectiveness of the proposed scheme.
IRJET- Enhancement of Image using Fuzzy Inference System for Remotely Sen...IRJET Journal
This document discusses using a fuzzy inference system to enhance remotely sensed multi-temporal images. It proposes a spectral resolution enhancement method (SREM) that uses fuzzy logic to increase image contrast and quality. The method involves fuzzifying the original image using triangular membership functions, then applying fuzzy rules to modify membership values. Finally, defuzzification converts the image back from the fuzzy membership plane to the pixel plane, producing an enhanced image with increased contrast. The approach is tested on eight image datasets and statistical analysis shows the fuzzy inference system produces enhanced images that improve the range of applications for remotely sensed data.
An Investigation towards Effectiveness in Image Enhancement Process in MPSoC IJECEIAES
The document discusses image enhancement techniques for use in multiprocessor systems-on-chip (MPSoC). It reviews existing image enhancement methods implemented on FPGA and identifies limitations like low accuracy. The paper proposes using advanced bus architectures like AMBA/AXI in MPSoC to improve communication between memory and input medical images for enhancement, reducing heterogeneity effects. It summarizes various image enhancement algorithms that could be implemented on reconfigurable FPGA hardware for use in MPSoC, including brightness control, contrast stretching, histogram equalization, and edge detection techniques.
Reversible Image Data Hiding with Contrast EnhancementIRJET Journal
This document proposes a reversible image data hiding technique with contrast enhancement. It aims to embed data into a cover image in a reversible manner while also enhancing the contrast of the cover image. The technique first calculates prediction errors of pixel values in the cover image. It then generates a histogram of the prediction errors and selects carriers for data embedding from peaks in the histogram. Binary secret data is embedded into the carriers by dynamically shifting the prediction error histogram. This allows data to be embedded while increasing cover image quality compared to other reversible data hiding methods. The original cover image can be recovered by extracting the embedded data and reversing the histogram shifts. The technique is meant to achieve a higher peak signal-to-noise ratio than the original cover image after data
IRJET- Handwritten Decimal Image Compression using Deep Stacked AutoencoderIRJET Journal
This document proposes using a deep stacked autoencoder neural network for compressing handwritten decimal image data. It involves training multiple autoencoders in sequence to form a deep network that can compress the high-dimensional input images into lower-dimensional encoded representations while minimizing information loss. The autoencoders are trained one layer at a time using scaled conjugate gradient descent. Testing on the MNIST handwritten digits dataset showed the deep stacked autoencoder achieved compression by encoding the 400-dimensional input images down to a 25-dimensional representation while maintaining good reconstruction accuracy, as measured by minimizing the mean squared error at each layer.
IRJET- Heuristic Approach for Low Light Image Enhancement using Deep LearningIRJET Journal
This document discusses a deep learning approach for enhancing low light images. It begins by describing the challenges of low light imaging such as low signal-to-noise ratio and increased noise. It then reviews existing image enhancement and denoising techniques that have limitations under extreme low light conditions. The proposed approach uses a convolutional neural network trained on a dataset of low and high exposure image pairs to learn an end-to-end image processing pipeline directly from raw sensor data. This aims to better handle noise and color biases compared to traditional pipelines. The goals are to enhance short exposure images while suppressing noise and applying proper color transformations.
Ieee projects 2012 2013 - Digital Image ProcessingK Sundaresh Ka
ieee projects download, base paper for ieee projects, ieee projects list, ieee projects titles, ieee projects for cse, ieee projects on networking,ieee projects 2012, ieee projects 2013, final year project, computer science final year projects, final year projects for information technology, ieee final year projects, final year students projects, students projects in java, students projects download, students projects in java with source code, students projects architecture, free ieee papers
This document summarizes a research paper that proposes a method to enhance the resolution of satellite images using discrete wavelet transform (DWT), interpolation, and inverse discrete wavelet transform (IDWT). Low resolution satellite images are decomposed into subbands using DWT. Bilinear interpolation is applied to each subband to increase resolution. IDWT is then used to combine the subbands into the enhanced, higher resolution output image. The method is tested on LANDSAT 8 images and evaluated using metrics like PSNR, MSE, and entropy. Results show the proposed method improves these metrics over other interpolation techniques, enhancing image quality and resolution.
The document discusses common image compression formats, including block transform and subband transform methods. For block transform, it describes the JPEG algorithm which uses discrete cosine transform (DCT) and quantization. For subband transform, it discusses developments like EZW and SPIHT, both of which use wavelet transforms and entropy coding like arithmetic coding. JPEG2000 is also covered as using tiling, DCT, and arithmetic coding like SPIHT.
IRJET - Review of Various Multi-Focus Image Fusion MethodsIRJET Journal
This document provides an overview of multi-focus image fusion methods. It discusses various multi-focus image fusion techniques in both the spatial and frequency domains. It reviews several papers on multi-focus image fusion using different methods like region mosaicking on laplacian pyramid (RMLP), discrete wavelet transform (DWT), principal component analysis (PCA), discrete cosine transform (DCT), and implementation on field programmable gate arrays (FPGAs). The document compares the advantages and issues of the techniques discussed in the reviewed papers. It provides context on applications of image fusion in areas like remote sensing, medical imaging, and more.
A Comparative Case Study on Compression Algorithm for Remote Sensing ImagesDR.P.S.JAGADEESH KUMAR
This document summarizes research on compression algorithms for remote sensing images. It begins with an abstract describing the challenges of transmitting large remote sensing images from sensors to networks. The document then reviews 18 different research papers on various compression algorithms for remote sensing images, including wavelet-based algorithms, fractal coding methods, and region-based approaches. It evaluates each algorithm's performance in compressing remote sensing images while maintaining quality. The document aims to perform a comparative case study of these different compression algorithms.
Estimation of Optimized Energy and Latency Constraint for Task Allocation in ...ijcsit
In Network on Chip (NoC) rooted system, energy consumption is affected by task scheduling and allocation
schemes which affect the performance of the system. In this paper we test the pre-existing proposed
algorithms and introduced a new energy skilled algorithm for 3D NoC architecture. An efficient dynamic
and cluster approaches are proposed along with the optimization using bio-inspired algorithm. The
proposed algorithm has been implemented and evaluated on randomly generated benchmark and real life
application such as MMS, Telecom and VOPD. The algorithm has also been tested with the E3S benchmark
and has been compared with the existing mapping algorithm spiral and crinkle and has shown better
reduction in the communication energy consumption and shows improvement in the performance of the
system. On performing experimental analysis of proposed algorithm results shows that average reduction
in energy consumption is 49%, reduction in communication cost is 48% and average latency is 34%.
Cluster based approach is mapped onto NoC using Dynamic Diagonal Mapping (DDMap), Crinkle and
Spiral algorithms and found DDmap provides improved result. On analysis and comparison of mapping of
cluster using DDmap approach the average energy reduction is 14% and 9% with crinkle and spiral.
Compressed Medical Image Transfer in Frequency DomainCSCJournals
A common approach to the medical image compression algorithm begins by separating the region of interests from the background of the medical images and then lossless and lossy compression schemes are applied on the ROI part and background respectively. The compressed files (ROI and background) are now transmitted through different media of communications (local host, Intranet and Internet) between the server and clients. In this work, a medical image transfer coding scheme based on lossless Haar wavelet transforms method is proposed. At first, the proposed scheme is tested on Intranet (for both RoI and background) in order to compare its results with Internet tests. An adaptive quantization algorithm is used to apply on quasi lossless ROI wavelet coefficients while a uniform quantization is used to apply on lossy background wavelet coefficients. Finally, the retained quantization indices are entropy encoded with an optimal variable coding algorithm. The test results have indicated that the performance of the proposed MITC via Intranet is much better than via Internet in terms of transferring time, while the quality of the reconstructed medical image remains constant despite the medium of communication. For best adopted parameters, a compressed medical image file (760 KB „³ 19.38 KB) is transmitted through Internet (bandwidth= 1024 kbps) with transfer time = 0.156 s while the uncompressed file is sent with transfer time = 6.192 s.
Improved Weighted Least Square Filter Based Pan Sharpening using Fuzzy LogicIRJET Journal
This document discusses an improved weighted least squares (WLS) filter-based pan sharpening method using fuzzy logic. It aims to address limitations of prior work by integrating an improved principal component analysis (PCA) algorithm with fuzzy logic for image fusion. The proposed algorithm is implemented in MATLAB using image processing toolbox. Comparative analysis shows the effectiveness of the proposed algorithm based on various performance metrics. It combines useful information from multi-focus images to generate a fused image with better quality.
IRJET- Kidney Stone Classification using Deep Neural Networks and Facilitatin...IRJET Journal
The document discusses classifying kidney stone images using deep neural networks and facilitating diagnosis using IoT. Kidney stone images are acquired and preprocessed by converting to grayscale, enhancing, and segmenting the area of interest. Texture features are extracted using active contour segmentation and classified using a deep neural network model. The results, including stone type and treatment recommendations, are sent to the cloud where doctors and patients can access them, allowing automated diagnosis without human intervention.
This document compares the performance of three lossless image compression techniques: Run Length Encoding (RLE), Delta encoding, and Huffman encoding. It tests these algorithms on binary, grayscale, and RGB images to evaluate compression ratio, storage savings percentage, and compression time. The results found that Delta encoding achieved the highest compression ratio and storage savings, while Huffman encoding had the fastest compression time. In general, the document evaluates and compares the performance of different lossless image compression algorithms.
Illumination Invariant Face Recognition System using Local Directional Patter...Editor IJCATR
The document proposes an illumination-robust face recognition system using local directional pattern (LDP) images and two-dimensional principal component analysis (2D-PCA). It extracts LDP images from face images as inputs to 2D-PCA for feature extraction, instead of using LDP for histogram feature extraction like previous works. Experimental results on the Yale B and CMU-PIE databases show the proposed approach achieves higher recognition accuracy than PCA and LBP-based methods, demonstrating its effectiveness in handling illumination variations. The maximum recognition rates are 96.43% for Yale B and 100% for CMU-PIE illumination sets.
IRJET- Exploring Image Super Resolution TechniquesIRJET Journal
This document discusses image super resolution techniques. It begins by defining super resolution as a technique that reconstructs a high resolution image from low resolution images. It then provides an overview of different super resolution methods including interpolation-based, reconstruction-based, and example-based (machine learning) techniques. The document evaluates state-of-the-art super resolution generative adversarial network (SRGAN) methods and their ability to generate realistic high resolution images from low resolution inputs. It also reviews the history and compares different super resolution techniques.
A Modified CNN-Based Face Recognition Systemgerogepatton
In this work, deep CNN based model have been suggested for face recognition. CNN is employed to extract
unique facial features and softmax classifier is applied to classify facial images in a fully connected layer
of CNN. The experiments conducted in Extended YALE B and FERET databases for smaller batch sizes
and low value of learning rate, showed that the proposed model has improved the face recognition
accuracy. Accuracy rates of up to 96.2% is achieved using the proposed model in Extended Yale B
database. To improve the accuracy rate further, preprocessing techniques like SQI, HE, LTISN, GIC and
DoG are applied to the CNN model. After the application of preprocessing techniques, the improved
accuracy of 99.8% is achieved with deep CNN model for the YALE B Extended Database. In FERET
Database with frontal face, before the application of preprocessing techniques, CNN model yields the
maximum accuracy of 71.4%. After applying the above-mentioned preprocessing techniques, the accuracy
is improved to 76.3%
A common goal of the engineering field of signal processing is to reconstruct a signal from a series of sampling measurements. In general, this task is impossible because there is no way to reconstruct a signal during the times
that the signal is not measured. Nevertheless, with prior knowledge or assumptions about the signal, it turns out to
be possible to perfectly reconstruct a signal from a series of measurements. Over time, engineers have improved their understanding of which assumptions are practical and how they can be generalized. An early breakthrough in signal processing was the Nyquist–Shannon sampling theorem. It states that if the signal's highest frequency is less than half of the sampling rate, then the signal can be reconstructed perfectly. The main idea is that with prior knowledge about constraints on the signal’s frequencies, fewer samples are needed to reconstruct the signal. Sparse sampling (also known as, compressive sampling, or compressed sampling) is a signal processing technique for efficiently acquiring and reconstructing a signal, by finding solutions tounder determined linear systems. This is based on the principle that, through optimization, the sparsity of a signal can be exploited to recover it from far fewer samples than required by the Shannon-Nyquist sampling theorem. There are two conditions under which recovery is possible.[1] The first one is sparsity which requires the signal to be sparse in some domain. The second one is incoherence which is applied through the isometric property which is sufficient for sparse signals Possibility
of compressed data acquisition protocols which directly acquire just the important information Sparse sampling (CS) is a fast growing area of research. It neglects the extravagant acquisition process by measuring lesser values to reconstruct the image or signal. Sparse sampling is adopted successfully in various fields of image processing and proved its efficiency. Some of the image processing applications like face recognition, video encoding, Image encryption and reconstruction are presented here.
This document discusses image compression using discrete wavelet transform (DWT) and principal component analysis (PCA). It first reviews several related works that use transforms like curvelet, wavelet and discrete cosine transform for image compression. It then describes preprocessing the input image using DWT to decompose it into sub-bands, and applying PCA on the high-frequency sub-bands to reduce dimensions and compress the image while preserving important boundaries. The algorithm is implemented and evaluated based on metrics like peak signal-to-noise ratio, standard deviation and entropy. Results show 95% accuracy in image identification from a database, though processing time increases significantly with database size.
This document presents Jeevn-Net, a new neural network architecture for brain tumor segmentation and overall survival prediction. Jeevn-Net uses a cascaded U-Net structure with two U-Nets and applies auto-encoder regularization. It takes in MRI scans and outputs a segmented tumor image with extracted features. Random forest regression is then used to predict survival based on these features. The network achieves state-of-the-art performance for brain tumor segmentation and survival prediction.
Reversible Data Hiding Using Contrast Enhancement ApproachCSCJournals
Reverse Data Hiding is a technique used to hide the object's data details. This technique is used to ensure the security and to protect the integrity of the object from any modification by preventing intended and unintended changes. Digital watermarking is a key ingredient to multimedia protection. However, most existing techniques distort the original content as a side effect of image protection. As a way to overcome such distortion, reversible data embedding has recently been introduced and is growing rapidly. In reversible data embedding, the original content can be completely restored after the removal of the watermark. Therefore, it is very practical to protect legal, medical, or other important imagery. In this paper a novel removable (lossless) data hiding technique is proposed. This technique is based on the histogram modification to produce extra space for embedding, and the redundancy in digital images is exploited to achieve a very high embedding capacity. This method has been applied to various standard images. The experimental results have demonstrated a promising outcome and the proposed technique achieved satisfactory and stable performance both on embedding capacity and visual quality. The proposed method capacity is up to 129K bits with PSNR between 42-45dB. The performance is hence better than most exiting reversible data hiding algorithms.
IRJET- MRI Image Processing Operations for Brain Tumor DetectionIRJET Journal
1. The document discusses computer-based approaches for detecting brain tumors from MRI images. It involves preprocessing the MRI image, segmenting the tumor region, extracting features from the tumor region, and classifying the tumor as cancerous or non-cancerous using techniques like neural networks and support vector machines.
2. The proposed method first preprocesses the MRI image using filters, thresholding and contrast adjustment. It then segments the tumor region using k-means clustering. Features of the tumor texture are extracted using gray level co-occurrence matrices. Neural networks and support vector machines are then used to classify tumors as cancerous or non-cancerous.
3. Results of applying the proposed method to MRI images are shown and
Real Time Face Recognition Based on Face Descriptor and Its ApplicationTELKOMNIKA JOURNAL
This paper presents a real time face recognition based on face descriptor and its application for door
locking. The face descriptor is represented by both local and global information. The local information, which
is the dominant frequency content of sub-face, is extracted by zoned discrete cosine transforms (DCT). While
the global information, which also is the dominant frequency content and shape information of the whole face,
is extracted by DCT and by Hu-moment. Therefore, face descriptor has rich information about a face image
which tends to provide good performance for real time face recognition. To decrease the dimensional size of
face descriptor, the predictive linear discriminant analysis (PDLDA) is employed and the face classification
is done by kNN. The experimental results show that the proposed real time face recognition provides good
performances which indicated by 98.30%, 21.99%, and 1.8% of accuracy, FPR, and FNR respectively. In
addition, it also needs short computational time (1 second).
IRJET - Automated 3-D Segmentation of Lung with Lung Cancer in CT Data using ...IRJET Journal
This document presents a novel robust active shape model (RASM) approach for automated 3D segmentation of lungs with lung cancer in CT data. The method consists of two main steps: 1) RASM matching is used to roughly segment the lung outline, with initial position found via skeletal structure detection. 2) Optimal surface finding further adapts the segmentation to the lung shape. Experiments on 30 datasets showed the proposed method achieved statistically better segmentation results than two commercial lung segmentation approaches, and is applicable to large shape models.
IRJET- Heuristic Approach for Low Light Image Enhancement using Deep LearningIRJET Journal
This document discusses a deep learning approach for enhancing low light images. It begins by describing the challenges of low light imaging such as low signal-to-noise ratio and increased noise. It then reviews existing image enhancement and denoising techniques that have limitations under extreme low light conditions. The proposed approach uses a convolutional neural network trained on a dataset of low and high exposure image pairs to learn an end-to-end image processing pipeline directly from raw sensor data. This aims to better handle noise and color biases compared to traditional pipelines. The goals are to enhance short exposure images while suppressing noise and applying proper color transformations.
Ieee projects 2012 2013 - Digital Image ProcessingK Sundaresh Ka
ieee projects download, base paper for ieee projects, ieee projects list, ieee projects titles, ieee projects for cse, ieee projects on networking,ieee projects 2012, ieee projects 2013, final year project, computer science final year projects, final year projects for information technology, ieee final year projects, final year students projects, students projects in java, students projects download, students projects in java with source code, students projects architecture, free ieee papers
This document summarizes a research paper that proposes a method to enhance the resolution of satellite images using discrete wavelet transform (DWT), interpolation, and inverse discrete wavelet transform (IDWT). Low resolution satellite images are decomposed into subbands using DWT. Bilinear interpolation is applied to each subband to increase resolution. IDWT is then used to combine the subbands into the enhanced, higher resolution output image. The method is tested on LANDSAT 8 images and evaluated using metrics like PSNR, MSE, and entropy. Results show the proposed method improves these metrics over other interpolation techniques, enhancing image quality and resolution.
The document discusses common image compression formats, including block transform and subband transform methods. For block transform, it describes the JPEG algorithm which uses discrete cosine transform (DCT) and quantization. For subband transform, it discusses developments like EZW and SPIHT, both of which use wavelet transforms and entropy coding like arithmetic coding. JPEG2000 is also covered as using tiling, DCT, and arithmetic coding like SPIHT.
IRJET - Review of Various Multi-Focus Image Fusion MethodsIRJET Journal
This document provides an overview of multi-focus image fusion methods. It discusses various multi-focus image fusion techniques in both the spatial and frequency domains. It reviews several papers on multi-focus image fusion using different methods like region mosaicking on laplacian pyramid (RMLP), discrete wavelet transform (DWT), principal component analysis (PCA), discrete cosine transform (DCT), and implementation on field programmable gate arrays (FPGAs). The document compares the advantages and issues of the techniques discussed in the reviewed papers. It provides context on applications of image fusion in areas like remote sensing, medical imaging, and more.
A Comparative Case Study on Compression Algorithm for Remote Sensing ImagesDR.P.S.JAGADEESH KUMAR
This document summarizes research on compression algorithms for remote sensing images. It begins with an abstract describing the challenges of transmitting large remote sensing images from sensors to networks. The document then reviews 18 different research papers on various compression algorithms for remote sensing images, including wavelet-based algorithms, fractal coding methods, and region-based approaches. It evaluates each algorithm's performance in compressing remote sensing images while maintaining quality. The document aims to perform a comparative case study of these different compression algorithms.
Estimation of Optimized Energy and Latency Constraint for Task Allocation in ...ijcsit
In Network on Chip (NoC) rooted system, energy consumption is affected by task scheduling and allocation
schemes which affect the performance of the system. In this paper we test the pre-existing proposed
algorithms and introduced a new energy skilled algorithm for 3D NoC architecture. An efficient dynamic
and cluster approaches are proposed along with the optimization using bio-inspired algorithm. The
proposed algorithm has been implemented and evaluated on randomly generated benchmark and real life
application such as MMS, Telecom and VOPD. The algorithm has also been tested with the E3S benchmark
and has been compared with the existing mapping algorithm spiral and crinkle and has shown better
reduction in the communication energy consumption and shows improvement in the performance of the
system. On performing experimental analysis of proposed algorithm results shows that average reduction
in energy consumption is 49%, reduction in communication cost is 48% and average latency is 34%.
Cluster based approach is mapped onto NoC using Dynamic Diagonal Mapping (DDMap), Crinkle and
Spiral algorithms and found DDmap provides improved result. On analysis and comparison of mapping of
cluster using DDmap approach the average energy reduction is 14% and 9% with crinkle and spiral.
Compressed Medical Image Transfer in Frequency DomainCSCJournals
A common approach to the medical image compression algorithm begins by separating the region of interests from the background of the medical images and then lossless and lossy compression schemes are applied on the ROI part and background respectively. The compressed files (ROI and background) are now transmitted through different media of communications (local host, Intranet and Internet) between the server and clients. In this work, a medical image transfer coding scheme based on lossless Haar wavelet transforms method is proposed. At first, the proposed scheme is tested on Intranet (for both RoI and background) in order to compare its results with Internet tests. An adaptive quantization algorithm is used to apply on quasi lossless ROI wavelet coefficients while a uniform quantization is used to apply on lossy background wavelet coefficients. Finally, the retained quantization indices are entropy encoded with an optimal variable coding algorithm. The test results have indicated that the performance of the proposed MITC via Intranet is much better than via Internet in terms of transferring time, while the quality of the reconstructed medical image remains constant despite the medium of communication. For best adopted parameters, a compressed medical image file (760 KB „³ 19.38 KB) is transmitted through Internet (bandwidth= 1024 kbps) with transfer time = 0.156 s while the uncompressed file is sent with transfer time = 6.192 s.
Improved Weighted Least Square Filter Based Pan Sharpening using Fuzzy LogicIRJET Journal
This document discusses an improved weighted least squares (WLS) filter-based pan sharpening method using fuzzy logic. It aims to address limitations of prior work by integrating an improved principal component analysis (PCA) algorithm with fuzzy logic for image fusion. The proposed algorithm is implemented in MATLAB using image processing toolbox. Comparative analysis shows the effectiveness of the proposed algorithm based on various performance metrics. It combines useful information from multi-focus images to generate a fused image with better quality.
IRJET- Kidney Stone Classification using Deep Neural Networks and Facilitatin...IRJET Journal
The document discusses classifying kidney stone images using deep neural networks and facilitating diagnosis using IoT. Kidney stone images are acquired and preprocessed by converting to grayscale, enhancing, and segmenting the area of interest. Texture features are extracted using active contour segmentation and classified using a deep neural network model. The results, including stone type and treatment recommendations, are sent to the cloud where doctors and patients can access them, allowing automated diagnosis without human intervention.
This document compares the performance of three lossless image compression techniques: Run Length Encoding (RLE), Delta encoding, and Huffman encoding. It tests these algorithms on binary, grayscale, and RGB images to evaluate compression ratio, storage savings percentage, and compression time. The results found that Delta encoding achieved the highest compression ratio and storage savings, while Huffman encoding had the fastest compression time. In general, the document evaluates and compares the performance of different lossless image compression algorithms.
Illumination Invariant Face Recognition System using Local Directional Patter...Editor IJCATR
The document proposes an illumination-robust face recognition system using local directional pattern (LDP) images and two-dimensional principal component analysis (2D-PCA). It extracts LDP images from face images as inputs to 2D-PCA for feature extraction, instead of using LDP for histogram feature extraction like previous works. Experimental results on the Yale B and CMU-PIE databases show the proposed approach achieves higher recognition accuracy than PCA and LBP-based methods, demonstrating its effectiveness in handling illumination variations. The maximum recognition rates are 96.43% for Yale B and 100% for CMU-PIE illumination sets.
IRJET- Exploring Image Super Resolution TechniquesIRJET Journal
This document discusses image super resolution techniques. It begins by defining super resolution as a technique that reconstructs a high resolution image from low resolution images. It then provides an overview of different super resolution methods including interpolation-based, reconstruction-based, and example-based (machine learning) techniques. The document evaluates state-of-the-art super resolution generative adversarial network (SRGAN) methods and their ability to generate realistic high resolution images from low resolution inputs. It also reviews the history and compares different super resolution techniques.
A Modified CNN-Based Face Recognition Systemgerogepatton
In this work, deep CNN based model have been suggested for face recognition. CNN is employed to extract
unique facial features and softmax classifier is applied to classify facial images in a fully connected layer
of CNN. The experiments conducted in Extended YALE B and FERET databases for smaller batch sizes
and low value of learning rate, showed that the proposed model has improved the face recognition
accuracy. Accuracy rates of up to 96.2% is achieved using the proposed model in Extended Yale B
database. To improve the accuracy rate further, preprocessing techniques like SQI, HE, LTISN, GIC and
DoG are applied to the CNN model. After the application of preprocessing techniques, the improved
accuracy of 99.8% is achieved with deep CNN model for the YALE B Extended Database. In FERET
Database with frontal face, before the application of preprocessing techniques, CNN model yields the
maximum accuracy of 71.4%. After applying the above-mentioned preprocessing techniques, the accuracy
is improved to 76.3%
A common goal of the engineering field of signal processing is to reconstruct a signal from a series of sampling measurements. In general, this task is impossible because there is no way to reconstruct a signal during the times
that the signal is not measured. Nevertheless, with prior knowledge or assumptions about the signal, it turns out to
be possible to perfectly reconstruct a signal from a series of measurements. Over time, engineers have improved their understanding of which assumptions are practical and how they can be generalized. An early breakthrough in signal processing was the Nyquist–Shannon sampling theorem. It states that if the signal's highest frequency is less than half of the sampling rate, then the signal can be reconstructed perfectly. The main idea is that with prior knowledge about constraints on the signal’s frequencies, fewer samples are needed to reconstruct the signal. Sparse sampling (also known as, compressive sampling, or compressed sampling) is a signal processing technique for efficiently acquiring and reconstructing a signal, by finding solutions tounder determined linear systems. This is based on the principle that, through optimization, the sparsity of a signal can be exploited to recover it from far fewer samples than required by the Shannon-Nyquist sampling theorem. There are two conditions under which recovery is possible.[1] The first one is sparsity which requires the signal to be sparse in some domain. The second one is incoherence which is applied through the isometric property which is sufficient for sparse signals Possibility
of compressed data acquisition protocols which directly acquire just the important information Sparse sampling (CS) is a fast growing area of research. It neglects the extravagant acquisition process by measuring lesser values to reconstruct the image or signal. Sparse sampling is adopted successfully in various fields of image processing and proved its efficiency. Some of the image processing applications like face recognition, video encoding, Image encryption and reconstruction are presented here.
This document discusses image compression using discrete wavelet transform (DWT) and principal component analysis (PCA). It first reviews several related works that use transforms like curvelet, wavelet and discrete cosine transform for image compression. It then describes preprocessing the input image using DWT to decompose it into sub-bands, and applying PCA on the high-frequency sub-bands to reduce dimensions and compress the image while preserving important boundaries. The algorithm is implemented and evaluated based on metrics like peak signal-to-noise ratio, standard deviation and entropy. Results show 95% accuracy in image identification from a database, though processing time increases significantly with database size.
This document presents Jeevn-Net, a new neural network architecture for brain tumor segmentation and overall survival prediction. Jeevn-Net uses a cascaded U-Net structure with two U-Nets and applies auto-encoder regularization. It takes in MRI scans and outputs a segmented tumor image with extracted features. Random forest regression is then used to predict survival based on these features. The network achieves state-of-the-art performance for brain tumor segmentation and survival prediction.
Reversible Data Hiding Using Contrast Enhancement ApproachCSCJournals
Reverse Data Hiding is a technique used to hide the object's data details. This technique is used to ensure the security and to protect the integrity of the object from any modification by preventing intended and unintended changes. Digital watermarking is a key ingredient to multimedia protection. However, most existing techniques distort the original content as a side effect of image protection. As a way to overcome such distortion, reversible data embedding has recently been introduced and is growing rapidly. In reversible data embedding, the original content can be completely restored after the removal of the watermark. Therefore, it is very practical to protect legal, medical, or other important imagery. In this paper a novel removable (lossless) data hiding technique is proposed. This technique is based on the histogram modification to produce extra space for embedding, and the redundancy in digital images is exploited to achieve a very high embedding capacity. This method has been applied to various standard images. The experimental results have demonstrated a promising outcome and the proposed technique achieved satisfactory and stable performance both on embedding capacity and visual quality. The proposed method capacity is up to 129K bits with PSNR between 42-45dB. The performance is hence better than most exiting reversible data hiding algorithms.
IRJET- MRI Image Processing Operations for Brain Tumor DetectionIRJET Journal
1. The document discusses computer-based approaches for detecting brain tumors from MRI images. It involves preprocessing the MRI image, segmenting the tumor region, extracting features from the tumor region, and classifying the tumor as cancerous or non-cancerous using techniques like neural networks and support vector machines.
2. The proposed method first preprocesses the MRI image using filters, thresholding and contrast adjustment. It then segments the tumor region using k-means clustering. Features of the tumor texture are extracted using gray level co-occurrence matrices. Neural networks and support vector machines are then used to classify tumors as cancerous or non-cancerous.
3. Results of applying the proposed method to MRI images are shown and
Real Time Face Recognition Based on Face Descriptor and Its ApplicationTELKOMNIKA JOURNAL
This paper presents a real time face recognition based on face descriptor and its application for door
locking. The face descriptor is represented by both local and global information. The local information, which
is the dominant frequency content of sub-face, is extracted by zoned discrete cosine transforms (DCT). While
the global information, which also is the dominant frequency content and shape information of the whole face,
is extracted by DCT and by Hu-moment. Therefore, face descriptor has rich information about a face image
which tends to provide good performance for real time face recognition. To decrease the dimensional size of
face descriptor, the predictive linear discriminant analysis (PDLDA) is employed and the face classification
is done by kNN. The experimental results show that the proposed real time face recognition provides good
performances which indicated by 98.30%, 21.99%, and 1.8% of accuracy, FPR, and FNR respectively. In
addition, it also needs short computational time (1 second).
IRJET - Automated 3-D Segmentation of Lung with Lung Cancer in CT Data using ...IRJET Journal
This document presents a novel robust active shape model (RASM) approach for automated 3D segmentation of lungs with lung cancer in CT data. The method consists of two main steps: 1) RASM matching is used to roughly segment the lung outline, with initial position found via skeletal structure detection. 2) Optimal surface finding further adapts the segmentation to the lung shape. Experiments on 30 datasets showed the proposed method achieved statistically better segmentation results than two commercial lung segmentation approaches, and is applicable to large shape models.
A principal component analysis-based feature dimensionality reduction scheme ...TELKOMNIKA JOURNAL
This document presents a principal component analysis (PCA)-based feature dimensionality reduction scheme for content-based image retrieval systems. The scheme was tested on image databases containing 10, 20, and 100 images. Each image was represented by a 174-dimensional feature vector comprising color, texture, and wavelet features. PCA was used to reduce the dimensionality of the feature vectors. Experimental results showed that an 80% reduction in dimensions achieved only a 3.45-7.40% loss in mean precision, depending on the database size. This demonstrates that PCA can significantly reduce the dimensionality of features with minimal impact on retrieval accuracy, addressing the curse of dimensionality problem for classifier-based relevance feedback schemes in content-based image retrieval systems.
A Novel Image Compression Approach Inexact Computingijtsrd
This work proposes a novel approach for digital image processing that relies on faulty computation to address some of the issues with discrete cosine transformation DCT compression. The proposed system has three processing stages the first employs approximated DCT for picture compression to eliminate all compute demanding floating point multiplication and to execute DCT processing with integer additions and, in certain cases, logical right left modifications. The second level reduces the amount of data that must be processed from the first level by removing frequencies that cannot be perceived by human senses. Finally, in order to reduce power consumption and delay, the third stage employs erroneous circuit level adders for DCT computation. A collection of structured pictures is compressed for measurement using the suggested three level method. Various figures of merit such as energy consumption, delay, power signal to noise ratio, average difference, and absolute maximum difference are compared to current compression techniques an error analysis is also carried out to substantiate the simulation findings. The results indicate significant gains in energy and time reduction while retaining acceptable accuracy levels for image processing applications. Sonam Kumari | Manish Rai "A Novel Image Compression Approach-Inexact Computing" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-6 | Issue-6 , October 2022, URL: https://www.ijtsrd.com/papers/ijtsrd52197.pdf Paper URL: https://www.ijtsrd.com/engineering/electrical-engineering/52197/a-novel-image-compression-approachinexact-computing/sonam-kumari
FACE PHOTO-SKETCH RECOGNITION USING DEEP LEARNING TECHNIQUES - A REVIEWIRJET Journal
This document reviews various deep learning techniques for face photo-sketch recognition. It summarizes several studies that used deep learning and other machine learning methods to match faces across photo and sketch domains. Feature injection and convolutional neural networks, knowledge distillation frameworks, relational graph modules, domain alignment embedding networks, and using 3D morphable models and CNNs for forensic sketch recognition are some of the techniques discussed. The studies aim to improve cross-domain face recognition accuracy, which remains challenging due to differences in photo and sketch representations. Accuracies ranging from 73-95% are reported for the various methods.
COMPOSITE IMAGELET IDENTIFIER FOR ML PROCESSORSIRJET Journal
The document proposes a composite imagelet identifier technique for machine learning processors that uses seam carving to manipulate edges and pixilation in images for processing. It discusses using existing algorithms like SSIM and Dijkstra's algorithm to calculate image energy and identify optimal seam locations for manipulation. The technique is evaluated using test images in MATLAB and is presented as having potential applications in areas like forestry, animal husbandry and safety monitoring.
The Computation Complexity Reduction of 2-D Gaussian FilterIRJET Journal
This document discusses reducing the computational complexity of a 2D Gaussian filter for image smoothing. It begins with an abstract that notes 2D Gaussian filters are commonly used for image smoothing but require heavy computational resources. It then proposes using fixed-point arithmetic rather than floating point to implement the filter on an FPGA, which can increase efficiency and decrease area and complexity. The document is divided into sections that cover the theory behind image filtering, image smoothing and sharpening, quality metrics for evaluation, and an energy scalable Gaussian smoothing filter architecture. It concludes by discussing results and benefits of implementing the filter using fixed-point arithmetic on an FPGA.
IRJET- 3D Object Recognition of Car Image DetectionIRJET Journal
This document summarizes research on 3D object recognition of car images using depth data from a Kinect sensor. The researchers used point cloud analysis techniques including VFH, CRH descriptors and ICP algorithms to match objects in 3D space. The approach involved preprocessing the point cloud to isolate individual objects, extracting descriptors, matching objects to models in a database, and verifying matches. Preliminary results showed the approach could successfully recognize objects like soda cans but performance was best at distances under 1 meter from the sensor. The goal is to enable applications like gesture controls and height estimation using 3D object detection.
Improving of Fingerprint Segmentation Images Based on K-MEANS and DBSCAN Clus...IJECEIAES
Nowadays, the fingerprint identification system is the most exploited sector of biometric. Fingerprint image segmentation is considered one of its first processing stage. Thus, this stage affects typically the feature extraction and matching process which leads to fingerprint recognition system with high accuracy. In this paper, three major steps are proposed. First, Soble and TopHat filtering method have been used to improve the quality of the fingerprint images. Then, for each local block in fingerprint image, an accurate separation of the foreground and background region is obtained by K-means clustering for combining 5-dimensional characteristics vector (variance, difference of mean, gradient coherence, ridge direction and energy spectrum). Additionally, in our approach, the local variance thresholding is used to reduce computing time for segmentation. Finally, we are combined to our system DBSCAN clustering which has been performed in order to overcome the drawbacks of K-means classification in fingerprint images segmentation. The proposed algorithm is tested on four different databases. Experimental results demonstrate that our approach is significantly efficacy against some recently published techniques in terms of separation between the ridge and non-ridge region.
Efficient Image Compression Technique using Clustering and Random PermutationIJERA Editor
Multimedia data compression is a challenging situation for compression technique, due to the possibility of loss
of data as well as it require large amount of storage place. The minimization of storage place and proper
transmission of these data need compression. In this dissertation we proposed a block based DWT image
compression technique using genetic algorithm and HCC code matrix. The HCC code matrix compressed into
two different set redundant and non-redundant which generate similar pattern of block coefficient. The similar
block coefficient generated by particle of swarm optimization. The process of particle of swarm optimization is
select for the optimal block of DWT transform function. For the experimental purpose we used some standard
image such as Lena, Barbara and cameraman image. The size of resolution of this image is 256*256. The source
of image is Google
Efficient Image Compression Technique using Clustering and Random PermutationIJERA Editor
Multimedia data compression is a challenging situation for compression technique, due to the possibility of loss
of data as well as it require large amount of storage place. The minimization of storage place and proper
transmission of these data need compression. In this dissertation we proposed a block based DWT image
compression technique using genetic algorithm and HCC code matrix. The HCC code matrix compressed into
two different set redundant and non-redundant which generate similar pattern of block coefficient. The similar
block coefficient generated by particle of swarm optimization. The process of particle of swarm optimization is
select for the optimal block of DWT transform function. For the experimental purpose we used some standard
image such as Lena, Barbara and cameraman image. The size of resolution of this image is 256*256. The source
of image is Google.
IRJET- Face Recognition using Machine LearningIRJET Journal
This document presents a modified CNN architecture for face recognition that adds two batch normalization operations to improve performance. The CNN extracts facial features using convolutional layers and max pooling, and classifies faces using a softmax classifier. The proposed approach was tested on a face database containing images of 4 individuals with varying lighting conditions. Experimental results showed the modified CNN with batch normalization achieved better recognition results than traditional methods.
Review paper on segmentation methods for multiobject feature extractioneSAT Journals
Abstract Feature extraction and representation plays a vital role in multimedia processing. It is still a challenge in computer vision system to extract ideal features that represents intrinsic characteristics of an image. Multiobject feature extraction system means a system that can extract features and locations of multiple objects in an image. In this paper we have discuss various methods to extract location and features of multiple objects and describe a system that can extract locations and features of multiple objects in an image by implementing an algorithm as hardware logic on a field-programmable gate array-based platform. There are many multiobject extraction methods which can be use for image segmentation based on motion, color intensity and texture. By calculating zeroth and first order moments of objects it is possible to obtain locations and sizes of multiple objects in an image. Keywords: multiobject extraction, image segmentation
Stereo matching based on absolute differences for multiple objects detectionTELKOMNIKA JOURNAL
This article presents a new algorithm for object detection using stereo camera system. The problem to get an accurate object detion using stereo camera is the imprecise of matching process between two scenes with the same viewpoint. Hence, this article aims to reduce the incorrect matching pixel with four stages. This new algorithm is the combination of continuous process of matching cost computation, aggregation, optimization and filtering. The first stage is matching cost computation to acquire preliminary result using an absolute differences method. Then the second stage known as aggregation step uses a guided filter with fixed window support size. After that, the optimization stage uses winner-takes-all (WTA) approach which selects the smallest matching differences value and normalized it to the disparity level. The last stage in the framework uses a bilateral filter. It is effectively further decrease the error on the disparity map which contains information of object detection and locations. The proposed work produces low errors (i.e., 12.11% and 14.01% nonocc and all errors) based on the KITTI dataset and capable to perform much better compared with before the proposed framework and competitive with some newly available methods.
FPGA Implementation of 2-D DCT & DWT Engines for Vision Based Tracking of Dyn...IJERA Editor
Real time motion estimation for tracking is a challenging task. Several techniques can transform an image into frequency domain, such as DCT, DFT and wavelet transform. Direct implementation of 2-D DCT takes N^4 multiplications for an N x N image which is impractical. The proposed architecture for implementation of 2-D DCT uses look up tables. They are used to store pre-computed vector products that completely eliminate the multiplier. This makes the architecture highly time efficient, and the routing delay and power consumption is also reduced significantly. Another approach, 2-D discrete wavelet transform based motion estimation (DWT-ME) provides substantial improvements in quality and area. The proposed architecture uses Haar wavelet transform for motion estimation. In this paper, we present the comparison of the performance of discrete cosine transform, discrete wavelet transform for implementation in motion estimation.
This document discusses using artificial neural networks and MATLAB 7.10 to develop an efficient system for sorting mechanical spare parts. It involves using wavelet transforms to extract features from images of parts, which are then used to train an artificial neural network. The neural network can accurately recognize parts based on their wavelet features with high efficiency. Simulation results show the system can successfully identify the name of a selected spare part from its image with a graphical output.
Artificial Neural Network (ANN) is a fast-growing method which has been used in different
industries during recent years. The main idea for creating ANN which is a subset of artificial
intelligence is to provide a simple model of human brain in order to solve complex scientific and
industrial problems. ANNs are high-value and low-cost tools in modelling, simulation, control,
condition monitoring, sensor validation and fault diagnosis of different systems. It have high
flexibility and robustness in modeling, simulating and diagnosing the behavior of rotating machines
even in the presence of inaccurate input data. They can provide high computational speed for
complicated tasks that require rapid response such as real-time processing of several simultaneous
signals. ANNs can also be used to improve efficiency and productivity of energy in rotating
equipment
Deep hypersphere embedding for real-time face recognitionTELKOMNIKA JOURNAL
With the advancement of human-computer interaction capabilities of robots, computer vision surveillance systems involving security yields a large impact in the research industry by helping in digitalization of certain security processes. Recognizing a face in the computer vision involves identification and classification of which faces belongs to the same person by means of comparing face embedding vectors. In an organization that has a large and diverse labelled dataset on a large number of epoch, oftentimes, creates a training difficulties involving incompatibility in different versions of face embedding that leads to poor face recognition accuracy. In this paper, we will design and implement robotic vision security surveillance system incorporating hybrid combination of MTCNN for face detection, and FaceNet as the unified embedding for face recognition and clustering.
Digital image enhancement by brightness and contrast manipulation using Veri...IJECEIAES
This document describes a proposed method for digitally enhancing images using brightness and contrast manipulation implemented in Verilog hardware description language. The method aims to improve low quality images impacted by low exposure and haze. It involves converting image files to hexadecimal, manipulating pixel brightness and contrast values using algorithms, and converting the output back to image format. The algorithms adjust brightness by adding a constant to pixel values and modify contrast by stretching the dynamic range of values. The method is evaluated on vehicle registration plate images and shows improvements over other enhancement methods based on quantitative and qualitative metrics.
IRJET- Face Recognition of Criminals for Security using Principal Component A...IRJET Journal
This document presents a face recognition system using principal component analysis to identify criminals at airports. The system is trained on images of known criminals collected from law enforcement agencies. It uses PCA for dimensionality reduction to generate eigenfaces from the training images. During testing, it generates an eigenface from the input image and calculates the Euclidean distance between this eigenface and the eigenfaces of the training images. It identifies the criminal as the one corresponding to the training image with the minimum distance, alerting authorities. The document outlines the methodology, including preprocessing steps like subtracting the mean face, and reviews prior work applying PCA and other algorithms to face recognition.
Similar to Face recognition using assemble of low frequency of DCT features (20)
Square transposition: an approach to the transposition process in block cipherjournalBEEI
The transposition process is needed in cryptography to create a diffusion effect on data encryption standard (DES) and advanced encryption standard (AES) algorithms as standard information security algorithms by the National Institute of Standards and Technology. The problem with DES and AES algorithms is that their transposition index values form patterns and do not form random values. This condition will certainly make it easier for a cryptanalyst to look for a relationship between ciphertexts because some processes are predictable. This research designs a transposition algorithm called square transposition. Each process uses square 8 × 8 as a place to insert and retrieve 64-bits. The determination of the pairing of the input scheme and the retrieval scheme that have unequal flow is an important factor in producing a good transposition. The square transposition can generate random and non-pattern indices so that transposition can be done better than DES and AES.
Hyper-parameter optimization of convolutional neural network based on particl...journalBEEI
The document proposes using a particle swarm optimization (PSO) algorithm to optimize the hyperparameters of a convolutional neural network (CNN) for image classification. The PSO algorithm is used to find optimal values for CNN hyperparameters like the number and size of convolutional filters. In experiments on the MNIST handwritten digit dataset, the optimized CNN achieved a testing error rate of 0.87%, which is competitive with state-of-the-art models. The proposed approach finds optimized CNN architectures automatically without requiring manual design or encoding strategies during training.
Supervised machine learning based liver disease prediction approach with LASS...journalBEEI
In this contemporary era, the uses of machine learning techniques are increasing rapidly in the field of medical science for detecting various diseases such as liver disease (LD). Around the globe, a large number of people die because of this deadly disease. By diagnosing the disease in a primary stage, early treatment can be helpful to cure the patient. In this research paper, a method is proposed to diagnose the LD using supervised machine learning classification algorithms, namely logistic regression, decision tree, random forest, AdaBoost, KNN, linear discriminant analysis, gradient boosting and support vector machine (SVM). We also deployed a least absolute shrinkage and selection operator (LASSO) feature selection technique on our taken dataset to suggest the most highly correlated attributes of LD. The predictions with 10 fold cross-validation (CV) made by the algorithms are tested in terms of accuracy, sensitivity, precision and f1-score values to forecast the disease. It is observed that the decision tree algorithm has the best performance score where accuracy, precision, sensitivity and f1-score values are 94.295%, 92%, 99% and 96% respectively with the inclusion of LASSO. Furthermore, a comparison with recent studies is shown to prove the significance of the proposed system.
A secure and energy saving protocol for wireless sensor networksjournalBEEI
The research domain for wireless sensor networks (WSN) has been extensively conducted due to innovative technologies and research directions that have come up addressing the usability of WSN under various schemes. This domain permits dependable tracking of a diversity of environments for both military and civil applications. The key management mechanism is a primary protocol for keeping the privacy and confidentiality of the data transmitted among different sensor nodes in WSNs. Since node's size is small; they are intrinsically limited by inadequate resources such as battery life-time and memory capacity. The proposed secure and energy saving protocol (SESP) for wireless sensor networks) has a significant impact on the overall network life-time and energy dissipation. To encrypt sent messsages, the SESP uses the public-key cryptography’s concept. It depends on sensor nodes' identities (IDs) to prevent the messages repeated; making security goals- authentication, confidentiality, integrity, availability, and freshness to be achieved. Finally, simulation results show that the proposed approach produced better energy consumption and network life-time compared to LEACH protocol; sensors are dead after 900 rounds in the proposed SESP protocol. While, in the low-energy adaptive clustering hierarchy (LEACH) scheme, the sensors are dead after 750 rounds.
Plant leaf identification system using convolutional neural networkjournalBEEI
This paper proposes a leaf identification system using convolutional neural network (CNN). This proposed system can identify five types of local Malaysia leaf which were acacia, papaya, cherry, mango and rambutan. By using CNN from deep learning, the network is trained from the database that acquired from leaf images captured by mobile phone for image classification. ResNet-50 was the architecture has been used for neural networks image classification and training the network for leaf identification. The recognition of photographs leaves requested several numbers of steps, starting with image pre-processing, feature extraction, plant identification, matching and testing, and finally extracting the results achieved in MATLAB. Testing sets of the system consists of 3 types of images which were white background, and noise added and random background images. Finally, interfaces for the leaf identification system have developed as the end software product using MATLAB app designer. As a result, the accuracy achieved for each training sets on five leaf classes are recorded above 98%, thus recognition process was successfully implemented.
Customized moodle-based learning management system for socially disadvantaged...journalBEEI
This study aims to develop Moodle-based LMS with customized learning content and modified user interface to facilitate pedagogical processes during covid-19 pandemic and investigate how teachers of socially disadvantaged schools perceived usability and technology acceptance. Co-design process was conducted with two activities: 1) need assessment phase using an online survey and interview session with the teachers and 2) the development phase of the LMS. The system was evaluated by 30 teachers from socially disadvantaged schools for relevance to their distance learning activities. We employed computer software usability questionnaire (CSUQ) to measure perceived usability and the technology acceptance model (TAM) with insertion of 3 original variables (i.e., perceived usefulness, perceived ease of use, and intention to use) and 5 external variables (i.e., attitude toward the system, perceived interaction, self-efficacy, user interface design, and course design). The average CSUQ rating exceeded 5.0 of 7 point-scale, indicated that teachers agreed that the information quality, interaction quality, and user interface quality were clear and easy to understand. TAM results concluded that the LMS design was judged to be usable, interactive, and well-developed. Teachers reported an effective user interface that allows effective teaching operations and lead to the system adoption in immediate time.
Understanding the role of individual learner in adaptive and personalized e-l...journalBEEI
Dynamic learning environment has emerged as a powerful platform in a modern e-learning system. The learning situation that constantly changing has forced the learning platform to adapt and personalize its learning resources for students. Evidence suggested that adaptation and personalization of e-learning systems (APLS) can be achieved by utilizing learner modeling, domain modeling, and instructional modeling. In the literature of APLS, questions have been raised about the role of individual characteristics that are relevant for adaptation. With several options, a new problem has been raised where the attributes of students in APLS often overlap and are not related between studies. Therefore, this study proposed a list of learner model attributes in dynamic learning to support adaptation and personalization. The study was conducted by exploring concepts from the literature selected based on the best criteria. Then, we described the results of important concepts in student modeling and provided definitions and examples of data values that researchers have used. Besides, we also discussed the implementation of the selected learner model in providing adaptation in dynamic learning.
Prototype mobile contactless transaction system in traditional markets to sup...journalBEEI
1) Researchers developed a prototype contactless transaction system using QR codes and digital payments to support physical distancing during the COVID-19 pandemic in traditional markets.
2) The system allows sellers and buyers in traditional markets to conduct fast, secure transactions via smartphones without direct cash exchange. Buyers scan sellers' QR codes to view product details and make e-wallet payments.
3) Testing showed the system's functions worked properly and users found it easy to use and useful for supporting contactless transactions and digital transformation of traditional markets. However, further development is needed to increase trust in digital payments for users unfamiliar with the technology.
Wireless HART stack using multiprocessor technique with laxity algorithmjournalBEEI
The use of a real-time operating system is required for the demarcation of industrial wireless sensor network (IWSN) stacks (RTOS). In the industrial world, a vast number of sensors are utilised to gather various types of data. The data gathered by the sensors cannot be prioritised ahead of time. Because all of the information is equally essential. As a result, a protocol stack is employed to guarantee that data is acquired and processed fairly. In IWSN, the protocol stack is implemented using RTOS. The data collected from IWSN sensor nodes is processed using non-preemptive scheduling and the protocol stack, and then sent in parallel to the IWSN's central controller. The real-time operating system (RTOS) is a process that occurs between hardware and software. Packets must be sent at a certain time. It's possible that some packets may collide during transmission. We're going to undertake this project to get around this collision. As a prototype, this project is divided into two parts. The first uses RTOS and the LPC2148 as a master node, while the second serves as a standard data collection node to which sensors are attached. Any controller may be used in the second part, depending on the situation. Wireless HART allows two nodes to communicate with each other.
Implementation of double-layer loaded on octagon microstrip yagi antennajournalBEEI
This document describes the implementation of a double-layer structure on an octagon microstrip yagi antenna (OMYA) to improve its performance at 5.8 GHz. The double-layer consists of two double positive (DPS) substrates placed above the OMYA. Simulation and experimental results show that the double-layer configuration increases the gain of the OMYA by 2.5 dB compared to without the double-layer. The measured bandwidth of the OMYA with double-layer is 14.6%, indicating the double-layer can increase both the gain and bandwidth of the OMYA.
The calculation of the field of an antenna located near the human headjournalBEEI
In this work, a numerical calculation was carried out in one of the universal programs for automatic electro-dynamic design. The calculation is aimed at obtaining numerical values for specific absorbed power (SAR). It is the SAR value that can be used to determine the effect of the antenna of a wireless device on biological objects; the dipole parameters will be selected for GSM1800. Investigation of the influence of distance to a cell phone on radiation shows that absorbed in the head of a person the effect of electromagnetic radiation on the brain decreases by three times this is a very important result the SAR value has decreased by almost three times it is acceptable results.
Exact secure outage probability performance of uplinkdownlink multiple access...journalBEEI
In this paper, we study uplink-downlink non-orthogonal multiple access (NOMA) systems by considering the secure performance at the physical layer. In the considered system model, the base station acts a relay to allow two users at the left side communicate with two users at the right side. By considering imperfect channel state information (CSI), the secure performance need be studied since an eavesdropper wants to overhear signals processed at the downlink. To provide secure performance metric, we derive exact expressions of secrecy outage probability (SOP) and and evaluating the impacts of main parameters on SOP metric. The important finding is that we can achieve the higher secrecy performance at high signal to noise ratio (SNR). Moreover, the numerical results demonstrate that the SOP tends to a constant at high SNR. Finally, our results show that the power allocation factors, target rates are main factors affecting to the secrecy performance of considered uplink-downlink NOMA systems.
Design of a dual-band antenna for energy harvesting applicationjournalBEEI
This report presents an investigation on how to improve the current dual-band antenna to enhance the better result of the antenna parameters for energy harvesting application. Besides that, to develop a new design and validate the antenna frequencies that will operate at 2.4 GHz and 5.4 GHz. At 5.4 GHz, more data can be transmitted compare to 2.4 GHz. However, 2.4 GHz has long distance of radiation, so it can be used when far away from the antenna module compare to 5 GHz that has short distance in radiation. The development of this project includes the scope of designing and testing of antenna using computer simulation technology (CST) 2018 software and vector network analyzer (VNA) equipment. In the process of designing, fundamental parameters of antenna are being measured and validated, in purpose to identify the better antenna performance.
Transforming data-centric eXtensible markup language into relational database...journalBEEI
eXtensible markup language (XML) appeared internationally as the format for data representation over the web. Yet, most organizations are still utilising relational databases as their database solutions. As such, it is crucial to provide seamless integration via effective transformation between these database infrastructures. In this paper, we propose XML-REG to bridge these two technologies based on node-based and path-based approaches. The node-based approach is good to annotate each positional node uniquely, while the path-based approach provides summarised path information to join the nodes. On top of that, a new range labelling is also proposed to annotate nodes uniquely by ensuring the structural relationships are maintained between nodes. If a new node is to be added to the document, re-labelling is not required as the new label will be assigned to the node via the new proposed labelling scheme. Experimental evaluations indicated that the performance of XML-REG exceeded XMap, XRecursive, XAncestor and Mini-XML concerning storing time, query retrieval time and scalability. This research produces a core framework for XML to relational databases (RDB) mapping, which could be adopted in various industries.
Key performance requirement of future next wireless networks (6G)journalBEEI
The document provides an overview of the key performance indicators (KPIs) for 6G wireless networks compared to 5G networks. Some of the major KPIs discussed for 6G include: achieving data rates of up to 1 Tbps and individual user data rates up to 100 Gbps; reducing latency below 10 milliseconds; supporting up to 10 million connected devices per square kilometer; improving spectral efficiency by up to 100 times through technologies like terahertz communications and smart surfaces; and achieving an energy efficiency of 1 pico-joule per bit transmitted through techniques like wireless power transmission and energy harvesting. The document outlines how 6G aims to integrate terrestrial, aerial and maritime communications into a single network to provide ubiquitous connectivity with higher
Noise resistance territorial intensity-based optical flow using inverse confi...journalBEEI
This paper presents the use of the inverse confidential technique on bilateral function with the territorial intensity-based optical flow to prove the effectiveness in noise resistance environment. In general, the image’s motion vector is coded by the technique called optical flow where the sequences of the image are used to determine the motion vector. But, the accuracy rate of the motion vector is reduced when the source of image sequences is interfered by noises. This work proved that the inverse confidential technique on bilateral function can increase the percentage of accuracy in the motion vector determination by the territorial intensity-based optical flow under the noisy environment. We performed the testing with several kinds of non-Gaussian noises at several patterns of standard image sequences by analyzing the result of the motion vector in a form of the error vector magnitude (EVM) and compared it with several noise resistance techniques in territorial intensity-based optical flow method.
Modeling climate phenomenon with software grids analysis and display system i...journalBEEI
This study aims to model climate change based on rainfall, air temperature, pressure, humidity and wind with grADS software and create a global warming module. This research uses 3D model, define, design, and develop. The results of the modeling of the five climate elements consist of the annual average temperature in Indonesia in 2009-2015 which is between 29oC to 30.1oC, the horizontal distribution of the annual average pressure in Indonesia in 2009-2018 is between 800 mBar to 1000 mBar, the horizontal distribution the average annual humidity in Indonesia in 2009 and 2011 ranged between 27-57, in 2012-2015, 2017 and 2018 it ranged between 30-60, during the East Monsoon, the wind circulation moved from northern Indonesia to the southern region Indonesia. During the west monsoon, the wind circulation moves from the southern part of Indonesia to the northern part of Indonesia. The global warming module for SMA/MA produced is feasible to use, this is in accordance with the value given by the validate of 69 which is in the appropriate category and the response of teachers and students through a 91% questionnaire.
An approach of re-organizing input dataset to enhance the quality of emotion ...journalBEEI
The purpose of this paper is to propose an approach of re-organizing input data to recognize emotion based on short signal segments and increase the quality of emotional recognition using physiological signals. MIT's long physiological signal set was divided into two new datasets, with shorter and overlapped segments. Three different classification methods (support vector machine, random forest, and multilayer perceptron) were implemented to identify eight emotional states based on statistical features of each segment in these two datasets. By re-organizing the input dataset, the quality of recognition results was enhanced. The random forest shows the best classification result among three implemented classification methods, with an accuracy of 97.72% for eight emotional states, on the overlapped dataset. This approach shows that, by re-organizing the input dataset, the high accuracy of recognition results can be achieved without the use of EEG and ECG signals.
Parking detection system using background subtraction and HSV color segmentationjournalBEEI
Manual system vehicle parking makes finding vacant parking lots difficult, so it has to check directly to the vacant space. If many people do parking, then the time needed for it is very much or requires many people to handle it. This research develops a real-time parking system to detect parking. The system is designed using the HSV color segmentation method in determining the background image. In addition, the detection process uses the background subtraction method. Applying these two methods requires image preprocessing using several methods such as grayscaling, blurring (low-pass filter). In addition, it is followed by a thresholding and filtering process to get the best image in the detection process. In the process, there is a determination of the ROI to determine the focus area of the object identified as empty parking. The parking detection process produces the best average accuracy of 95.76%. The minimum threshold value of 255 pixels is 0.4. This value is the best value from 33 test data in several criteria, such as the time of capture, composition and color of the vehicle, the shape of the shadow of the object’s environment, and the intensity of light. This parking detection system can be implemented in real-time to determine the position of an empty place.
Quality of service performances of video and voice transmission in universal ...journalBEEI
The universal mobile telecommunications system (UMTS) has distinct benefits in that it supports a wide range of quality of service (QoS) criteria that users require in order to fulfill their requirements. The transmission of video and audio in real-time applications places a high demand on the cellular network, therefore QoS is a major problem in these applications. The ability to provide QoS in the UMTS backbone network necessitates an active QoS mechanism in order to maintain the necessary level of convenience on UMTS networks. For UMTS networks, investigation models for end-to-end QoS, total transmitted and received data, packet loss, and throughput providing techniques are run and assessed and the simulation results are examined. According to the results, appropriate QoS adaption allows for specific voice and video transmission. Finally, by analyzing existing QoS parameters, the QoS performance of 4G/UMTS networks may be improved.
A review on techniques and modelling methodologies used for checking electrom...nooriasukmaningtyas
The proper function of the integrated circuit (IC) in an inhibiting electromagnetic environment has always been a serious concern throughout the decades of revolution in the world of electronics, from disjunct devices to today’s integrated circuit technology, where billions of transistors are combined on a single chip. The automotive industry and smart vehicles in particular, are confronting design issues such as being prone to electromagnetic interference (EMI). Electronic control devices calculate incorrect outputs because of EMI and sensors give misleading values which can prove fatal in case of automotives. In this paper, the authors have non exhaustively tried to review research work concerned with the investigation of EMI in ICs and prediction of this EMI using various modelling methodologies and measurement setups.
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...IJECEIAES
Medical image analysis has witnessed significant advancements with deep learning techniques. In the domain of brain tumor segmentation, the ability to
precisely delineate tumor boundaries from magnetic resonance imaging (MRI)
scans holds profound implications for diagnosis. This study presents an ensemble convolutional neural network (CNN) with transfer learning, integrating
the state-of-the-art Deeplabv3+ architecture with the ResNet18 backbone. The
model is rigorously trained and evaluated, exhibiting remarkable performance
metrics, including an impressive global accuracy of 99.286%, a high-class accuracy of 82.191%, a mean intersection over union (IoU) of 79.900%, a weighted
IoU of 98.620%, and a Boundary F1 (BF) score of 83.303%. Notably, a detailed comparative analysis with existing methods showcases the superiority of
our proposed model. These findings underscore the model’s competence in precise brain tumor localization, underscoring its potential to revolutionize medical
image analysis and enhance healthcare outcomes. This research paves the way
for future exploration and optimization of advanced CNN models in medical
imaging, emphasizing addressing false positives and resource efficiency.
Introduction- e - waste – definition - sources of e-waste– hazardous substances in e-waste - effects of e-waste on environment and human health- need for e-waste management– e-waste handling rules - waste minimization techniques for managing e-waste – recycling of e-waste - disposal treatment methods of e- waste – mechanism of extraction of precious metal from leaching solution-global Scenario of E-waste – E-waste in India- case studies.
Understanding Inductive Bias in Machine LearningSUTEJAS
This presentation explores the concept of inductive bias in machine learning. It explains how algorithms come with built-in assumptions and preferences that guide the learning process. You'll learn about the different types of inductive bias and how they can impact the performance and generalizability of machine learning models.
The presentation also covers the positive and negative aspects of inductive bias, along with strategies for mitigating potential drawbacks. We'll explore examples of how bias manifests in algorithms like neural networks and decision trees.
By understanding inductive bias, you can gain valuable insights into how machine learning models work and make informed decisions when building and deploying them.
Using recycled concrete aggregates (RCA) for pavements is crucial to achieving sustainability. Implementing RCA for new pavement can minimize carbon footprint, conserve natural resources, reduce harmful emissions, and lower life cycle costs. Compared to natural aggregate (NA), RCA pavement has fewer comprehensive studies and sustainability assessments.
Comparative analysis between traditional aquaponics and reconstructed aquapon...bijceesjournal
The aquaponic system of planting is a method that does not require soil usage. It is a method that only needs water, fish, lava rocks (a substitute for soil), and plants. Aquaponic systems are sustainable and environmentally friendly. Its use not only helps to plant in small spaces but also helps reduce artificial chemical use and minimizes excess water use, as aquaponics consumes 90% less water than soil-based gardening. The study applied a descriptive and experimental design to assess and compare conventional and reconstructed aquaponic methods for reproducing tomatoes. The researchers created an observation checklist to determine the significant factors of the study. The study aims to determine the significant difference between traditional aquaponics and reconstructed aquaponics systems propagating tomatoes in terms of height, weight, girth, and number of fruits. The reconstructed aquaponics system’s higher growth yield results in a much more nourished crop than the traditional aquaponics system. It is superior in its number of fruits, height, weight, and girth measurement. Moreover, the reconstructed aquaponics system is proven to eliminate all the hindrances present in the traditional aquaponics system, which are overcrowding of fish, algae growth, pest problems, contaminated water, and dead fish.
2. ISSN: 2302-9285
Bulletin of Electr Eng and Inf, Vol. 8, No. 2, June 2019 : 541 – 550
542
The DCT has the ability to divide the information into a small number of coefficients on upper left
side know as low frequency component. Compared to Karhunen Loeve Transform (KLT), DCT have
advantage in potential smaller dimension, better processing time, and compatibility with encoded data such
as jpeg. In this paper we utilize local information by using block base DCT to eliminate the effect of
expression, illumination, pose and occlusion variations. Among all DCT coefficients, the first coefficient is
called DC value that holds the entire energy as well as perceptual information of an image block.
Feature dimensional reduction based on Principle Component Analysis (PCA) is an efficient way to
produce low dimensional feature space. This process further reduces feature dimensionality in the feature
space after extracted using Discrete Cosine Transform (DCT) as stated in [2]. Principal Components are
linear combinations of optimally weighted observed variables and is less complicated compared to Linear
Discriminant Analysis (LDA) and Independent Component Analysis (ICA). Normally for this kind of feature
extraction the classification process is done by using the Euclidean distance classifier. This approach will
reduce the complexity of the classifier algorithm and produce better processing speed.
The implementation of the algorithm in DSP processor such as TMS320C6713 produces low-cost
and fast processing time. Texas Instrument (TI) provided all required architecture that is suitable for many
DSP applications such as image and signal analysis. The advantage of the C6x microprocessor is a very-long-
instruction-word (VLIW), which can execute multiple processes in a single instruction. The C6x architecture
is very well suited for numerically intensive calculations, where it is under the TMS320C6000 family. In the
experiment analysis, TMS320C6713 is used because of its high performance and suitability for this kind
of algorithm.
This paper proposes a new method of feature extraction to produce high discrimination feature space
for real time face recognition system using local features extracted in face local regions. The main
contributions of this paper are as follows:
a. Local feature extraction using low frequency information extracted in local region of face image to
produce high discrimination feature.
b. Assemble of local feature using discrete cosine transform and principle components analysis to reduce
noise and redundant information.
The propose method has been tested using ORL database. The success of using small features space
is demonstrated in term of comparative performance against the other biometrics traits. The paper is
organized as follows: Section 2 discusses about our proposed method; Section 3 contains the experimental
analysis and discussion; and Section 4 is conclutions.
2. FRAME WORK OF THE PROPOSED METHOD
The propose multiple stage reduction process at feature level is able to produce small dimension of
features. A matrix of low frequency features and simple statistical tool is used to capture the fundamental of
statistical evidence in feature vector as shows in Figure 1.
Figure 1. The block diagram of the proposed method implementing new matrix vector of low frequency
features and double vector reduction
The advantage of the propose method:
a. Low frequency of DCT coefficients. This approach produces more information which is important for
classification and also robust to illumination and pose variations. The extracted features from all block
windows are rearrange in a new matrix with respect to the low frequency.
3. Bulletin of Electr Eng and Inf ISSN: 2302-9285
Face recognition using assemble of low frequency of DCT features (Raja Abdullah Raja Ahmad)
543
b. The multiple stage of reduction reduces the size of feature vector. The substantial reduction amount of
features will increase the performance over the conventional method.
c. Local features extraction based on DCT are computed in several image regions. This method separates
the image into several regions that has different discrimination power. The extracted information in
small window will increase computational speed.
The block diagram in Figure 1 shows all the important stage from input image until the classification
process. At the pre-processing stage, all images are subdivided into a block window and each window is
transformed to the DCT domain. Low frequency features are preserved by selecting several DCT coefficients
using zig-zag scanning approach. PCA is then applied in the next stage to optimize the reduction of feature
dimension by selecting the most eigenvalues that represent the image. The two stage vector reduction
mention above occurred in DCT domain and linier projection method.
2.1. Extraction of local features
The feature extraction is important in face recognition as it is used to capture the informative
component exist in face image. The extracted features must be valuable to the next process, such as image
projection and subject classification with allowable error rate. Furthermore, the feature extraction should be
effective with regards to computational resource such as memory and processing time.
Extraction of features can be done in several ways; 1) Holistic. 2) Local feature. Holistic feature
generally tends to produce high dimensional feature, which makes it powerless to directly classify in the
feature space. Therefore, method such as DCT and PCA are employed in holistic-base method as
dimensional reduction techniques [2-4].
Another approach to extract holistic information is feature-based approach such as Wavelet
transform [5], Discrete cosine transform [6], and Fourier transform [7]. In this approach the features are
extracted from spatial frequency technique. The entire image is converted into the frequency domain then
only some coefficients are preserved.
Nowadays several researchers have started to implement local features for biometric recognition.
This approach uses several local observations obtained from an image to represent the image features [8, 9].
The advantages to the holistic features it has lower dimensional features, and the local features are more
robust to the illumination, variation, and occlusion as spatially in face recognition. Local Binary Pattern
(LBP) is one of feature base method which used to examine the pattern of a biometric face representation
into histogram.
Another method is component based approach where the images are divided into several blocks. The
image from each block are extracted independently and then used for classification process. Several approach
using this method are Gaborfeatures was develop by [10], component based LDA [11] and modular PCA
[12]. Local features based on frequency coefficient can be extracted using Discrete Cosine Transform. In this
method a face image is divided into sub block then another process is performed to extract features from low
frequency band. A successful method based on frequency coefficient was developed base on statistical model
such as a Principle Component Analysis (PCA) [13] and Linear Discriminant Analysis (LDA) [14].
In this paper, we utilize the local feature based on frequency coefficient extracted using DCT
method. Sub block based feature are robust to the illumination and pose variation compared to global
features. Furthermore, to archive less computational cost our proposed method only used 3 coefficients from
a 28x46 window frame with no overlapping block. The first coefficient is preserve inside the matrix shown in
Figure 2. This coefficient is known as DC component which representing the average of an image, while the
rest are high frequency components of image. Method in [15] proved that the high frequency information by
itself is insufficient for good face recognition performance. The rejection of high frequency component also
causes the image to be robust to scale variations which is required in face recognition system. The practically
observation and experiment conducted by [16] show the DC coefficient holding 95% of the energy and
proofed the amplitudes are directly related to the energies which carry the information in an image. The
general equation for DCT is shown in (1). If an image f(x,y), with dimension MxN will produce a 2D-DCT
F(u,v) that has the dimension MxN and is computed as:
( ) ∑ ∑ ( )
( ) ( )
(1)
where: {
√ ⁄
√ ⁄
{
√ ⁄
√ ⁄
4. ISSN: 2302-9285
Bulletin of Electr Eng and Inf, Vol. 8, No. 2, June 2019 : 541 – 550
544
Figure 2. The structure of new matrix of low frequency feature. The components ( ) are group
together after extract from all sub-windows, then concatenated to represent face image
2.2. Double vector reduction
ORL face database contains a set of face images taken between April 1992 and April 1994 at the lab
The images are organized into 40 directories (one for each subject), and Each directory contains 10 different
pose of a person. The size of each image is 92x112 pixels, for a total is 10,304 pixels, with 256 grey levels
per pixel.
High dimensional vector caused recognition proses slow and not applicable for low computational
resource such DSP board. To avoid the situation occurred we proposed double reduction to reduce; 1) feature
vector and 2) feature space.
In DCT stages only three coefficients are selected from each sub-block window and total
coefficients used to represent a single face image are 24 which is 0.233% from the total coefficient size
(10,304). This can save a lot of computational resources such as RAM, ROM and processing time. The next
features reduction process on PCA stage. Using PCA, the 24 coefficients are reducing by projecting a new
dimension space is 10.
The detail step of PCA are show in (2) until (6). Consider a matrix NxN face image Γ(x,y) as a vector
of dimension N2
, so the image can be thought as a point in N2
dimensional space. A database of M images can
therefore be mapped to a collection of points in this high-dimensional “face space” as
∑ (2)
where: M is the number of images in the training phase
Compute zero mean image for each train and test images as shown in (3):
(3)
where:
The covariance matrix C of the data set is defined by (4):
∑ (4)
where: the matrix .
The next process is to find the eigenvectors of . These vectors determine the linear
combination of the training set face images to form Eigenfaces . A new face image ( ) is transformed to
its eigenface component (i.e., projected into “face space”) using the following (6):
( ) (6)
where: is the -th coordinate of the
5. Bulletin of Electr Eng and Inf ISSN: 2302-9285
Face recognition using assemble of low frequency of DCT features (Raja Abdullah Raja Ahmad)
545
2.3. Classification process
Classification is a process to identify the unknown face which is correlated to the subject face. This
process uses both projection test and projection train that are produced by Principle Component
Analysis (PCA).
Euclidean distance is one of the simplest and faster classifier as compared to other classifiers. To
recognize unknown faces, the Euclidian distance method is used to find the minimum distance between data
projection; face tests and the face train. Euclidean distance is defined as the straight-line distance between
two points as given in (7). The smallest value of ϵ_k distance will make the assumption that they are from the
same class.
(7)
where: describe the -th face class
3. RESULTS AND ANALYSIS
The ORL data set consist of 40 persons and contain 10 set of images for each person. The subjects
comprise of 4 females and 36 males. For some subject the images were taken with varying lighting, at
different times, different poses, facial expressions such as; open/closed eyes, smiling/not smiling, and facial
details; with glasses/no glasses. These images include up to of facial titling and rotation. Some
differences in scale and changes in brightness also occur. For the background, all images were taken against a
dark homogeneous with the subjects in an upright, frontal position (with tolerance for some side movement).
The experiment was split into two stage which is personal computer (PC) and single board computer (SBC)
TMS320C6713.
3.1. PC based experiment
In first experiment the set is manually select to find which set has the highest and the lowest
recognition rate where one image used for test and others images used for train, the DCT coefficient and
PCA dimension is fixed to 20. Table 1 shown the comparison Accuracy (%) and Times (s) for Each Selected
Set of Train (Tr) and Test (Ts) Image.
The observation from Table 1 can be conclude that the best accuracy (%) is 100% with a lowest time
consumption 0.72 seconds (s) is Set Image 7 and the worst accuracy is 95% with the highest time
consumption is 0.75s of Set Image 1. The experiment continues with those two selected image (Set Image 7
and Set Image 1) shown in Table 1, where their accuracy is compared based on the different number of DCT
coefficients, PCA coefficients and number of training images. this section, it is explained the results of
research and at the same time is given the comprehensive discussion.
Table 1. Comparison accuracy and times for each selected set of train and test image
DCT PCA (%) (s) (Ts) (Tr)
20 20 95 0.7508 1 2,3,4… 10
20 20 95 0.7086 2 Except 2
20 20 100 0.7729 3 Except 3
20 20 97.5 0.7099 4 Except 4
20 20 100 0.724 5 Except 5
20 20 97.5 0.7201 6 Except 6
20 20 100 0.7233 7 Except 7
20 20 97.5 0.7148 8 Except 8
20 20 97.5 0.6947 9 Except 8
20 20 100 0.7666 10 Except 10
The objective of second experiment is to find the relation between accuracy, execution time, and the
number of training image as shown in Figure 3. From the observation execution time increase when number
of training increase, then this will affect the system performance. The highest recognition rate achieved when
using nine of training image, which is 100% (set 7) and 95% (set1), then decaying when using less of training
image. However, the best accuracy rate is important to the system. The nine train images are selected as it is
applied in the proposed system.
6. ISSN: 2302-9285
Bulletin of Electr Eng and Inf, Vol. 8, No. 2, June 2019 : 541 – 550
546
Figure 3. The relationship between accuracy, execution time and number of training image
In the third experiment PCA dimension fixed to 20 and DCT coefficient is varied from 3 to 100. The
result shown in Figure 4. From observation most result remains the same 100% and 95% respectively for set
7 and set 5 even if the DCT coefficient is varied from 3 to 100, but the time required to execute the task is
increased when more coefficients are used in the process. For best performance and less complex system, the
proposed method only 3 DCT coefficients from each sub-block were used.
Figure 4. Relationship between accuracy, execution time and DCT coefficient
Figure 5 shows the result of fourth experiment the DCT coefficient is fixed to 20 and then the PCA
dimension varies from 1 to 100. The start of optimum accuracy, which is 100% for Set Image 7 and 95% for
Set Image 1, is when the PCA dimension equals to 10 and the accuracy maintains until the dimension is 100.
The execution time is proportional to the PCA dimension. The increasing of PCA dimension give more affect
system execution time compared to the increasing of DCT coefficient. The execution stime for 100 DCT
coefficient versus 100 PCA dimension is 1.8 second and 3.1 second respectively. Based on the analysis
result, only 10 of the PCA dimensions are used in the proposed method.
0
0,2
0,4
0,6
0,8
0
20
40
60
80
100
120
9 8 7 6 5 4 3 2 1
Time
(s)
Accuracy
(%)
Number of Image
Accuracy and Time vs number of train Image (seven and one)
Accuracy 7 Accuracy 1 Time 7 Time 1
0
0,5
1
1,5
2
93
94
95
96
97
98
99
3 10 20 30 40 50 60 70 80 90 100
Time
(s)
Accuracy
(%)
DCT Coefficient
Accuracy and Time VS DCT Coefficient of Image (Seven and One)
Accuracy 7 Accuracy 1 Time 7 Time 1
7. Bulletin of Electr Eng and Inf ISSN: 2302-9285
Face recognition using assemble of low frequency of DCT features (Raja Abdullah Raja Ahmad)
547
Figure 5. Relationship between accuracy and execution time and PCA dimension
The fifth experiment explains the benefit of local features extraction using DCT compared to holistic
extraction using DCT in terms of processing time. From the review of related papers, most of them
concluded that local features returns better results than holistic with regards to pose and illumination
problems [17, 18]. The result in Figure 6 shown the difference in time always increases proportional to the
number of extraction images. In this experiment we try up to five samples, the holistic extraction required
29.24s longer then local feature.
Figure 6. Holistic versus Local features in term of extraction time
The performance of the recognition system that using 3 DCT coefficients from each sub-block
image and 10 PCA dimension is tested and detail shown in Table 2. When Set Image 7 is tested, the face
recognition performed is 100% and, when the Set Image 1 is tested, the face recognition performance is 95%
and the recognition process only required around 0.33s to recognize 40 people.
Table 2. Analysis performance and execution time using 3 coefficients and 10 pca dimension
DCT PCA (%) (s) Ts Tr
3 10 100 0.33 7 1,2,3,4,5,6,8,9,10
3 10 95 0.32 1 2,3,4,5,6,7,8,9,10
0
0,5
1
1,5
2
2,5
3
3,5
0
20
40
60
80
100
120
1 10 20 30 40 50 60 70 80 90 100
Time
(s)
Accuracy
(%)
PCA Dimentions
Accuracy and Time VS PCA Dimension of Image (Seven and One)
Accuracy 7 Accuracy 1 Time 7 Time 1
8. ISSN: 2302-9285
Bulletin of Electr Eng and Inf, Vol. 8, No. 2, June 2019 : 541 – 550
548
3.2. SBC TMS320C6713 based experiment
In this section, the analysis focused on the TMS320C6713 DSK board to measures the execution
time and accuracy. In this experiment only used 30 face images, 3 images used for test and other 27 images
used for train.
When both DCT coefficient and PCA dimension are 30, the execution time for PC is 23.96ms and
74.24ms for the DSP board, and then after reducing the DCT coefficient and PCA dimensions respectively to
3 and 10. The time for the PC reduces up to 2.17ms and the DSP board is reduced to 4.43ms. The proposed
method can reduce a lot of execution time, this can make system efficient and relevant for real time
application. The detail of analysis result shown in Table 3.
Table 3. Compare result between DSP board and offline using image set seven
DCT PCA Ts:Tr SBC (ms) PC (ms) SBC (%) PC (%)
30 30 3:27 74.24 23.96 100 100
3 10 3:27 4.43 2.17 100 100
We believe if we use a DSP board that has the same speed as PC, the execution time for the DSP
board is more than five times faster than PC because the PC’s using Core i5 with 8 Gigabyte of RAM and
measured speed is 2.5GHz. where, DSP board’s measured speed is 225MHz. Table 4 shown the comparison
of several existing methods with the proposed method.
Table 4. Comparison result of the existing with the top recognition rate of the proposed method
Methods Modalities Accuracy (%)
Sun et.al.,[21] ORL 96
Bozorgtabar et.al.,[20] ORL 96.5
Bag et.al.,[19] ORL 96.7
Wu FengXiang,[22] ORL 98.7
Jawal Nagil et.al.,[23] ORL 98.9
Hafiz Imtiaz et.al.,[24] ORL 99.75
Proposed method ORL 100
4. CONCLUSION
Developing a face recognition system is a challenge because the faces always changes due to
expression, direction, light, and scale. This paper focuses on the local features extraction approach, which
divides the facial image based on the informative zones. The analysis using ORL shows that the result is
outperform, which is the highest recognition rate is 100% for the best selected test image and 95% for the
worst selected test image. Besides that, execution time is to recognize 40 people only requires 0.3313 second.
The Image Set 7 and set 1 are used in this experiment to find the best and worth recognition rate, then assume
recognition rate of the others set of image are in between this two set. The 95% mean 38/40 person are
correctly recognized. In this experiment, the key of success is training image. Compare to others paper
[18-20] they used less of training image instead of nine of training image for each person. However, feature
space is still small because the proposed method only extract three of DCT coefficients from each patch then
3x8=24 coefficients per face image. After PCA reduction only 10 features per a face image used for
classification. In other word the system was able to extract and select the valuable features from face image
to get high recognition rate, at the same time reduce features space size and less execution time, thus proving
this system is simpler, faster, and have a high recognition rate.
ACKNOWLEDGEMENTS
This research is supported by Ministry of Education Malaysia financial under the Fundamental
Research Grant Scheme (FRGS) Grant No: 9003-00583.
REFERENCES
[1] M. R. Mohd. Zainal, H. Husain, S. A. Samad, and A. Hussain, “Face verification using multiple localized face
features,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol.
8237 LNCS, pp. 97–103, 2013.
[2] W. Chen, M. J. Er, and S. Wu, “PCA and LDA in DCT domain,” Pattern Recognit. Lett., vol. 26, no. 15,
pp. 2474–2482, 2005.
9. Bulletin of Electr Eng and Inf ISSN: 2302-9285
Face recognition using assemble of low frequency of DCT features (Raja Abdullah Raja Ahmad)
549
[3] Z. Fan et al., "Modified Principal Component Analysis: An Integration of Multiple Similarity Subspace Models,"
in IEEE Transactions on Neural Networks and Learning Systems, vol. 25, no. 8, pp. 1538-1552, Aug. 2014.
[4] N. Kwak, "Principal Component Analysis Based on L1-Norm Maximization," in IEEE Transactions on Pattern
Analysis and Machine Intelligence, vol. 30, no. 9, pp. 1672-1680, Sept. 2008.
[5] M. M. Mukhedkar, “Fast Face Recognition Based on Wavelet Transform on PCA,” Int. Conf. Energy Syst. Appl.
(ICESA 2015), no. Icesa, pp. 761–764, 2015.
[6] S. Dabbaghchian, M. P. Ghaemmaghami, and A. Aghagolzadeh, “Feature extraction using discrete cosine
transform and discrimination power analysis with a face recognition technology,” Pattern Recognit., vol. 43, no. 4,
pp. 1431–1440, 2010.
[7] A. K. Jha, R. Gupta and D. Saini, "Face Recognition: A Fourier Transform and SVD Based Approach," 2013 5th
International Conference and Computational Intelligence and Communication Networks, Mathura, 2013,
pp. 205-209.
[8] N. Wang, J. Li, D. Tao, X. Li, and X. Gao, “Heterogeneous image transformation,” Pattern Recognit. Lett., vol. 34,
no. 1, pp. 77–84, 2013.
[9] N. Wang, D. Tao, X. Gao, X. Li, and J. Li, “A comprehensive survey to face hallucination,” Int. J. Comput. Vis.,
vol. 106, no. 1, pp. 9–30, 2014.
[10] L. A. Cament, F. J. Galdames, K. W. Bowyer, and C. A. Perez, “Face recognition under pose variation with local
Gabor features enhanced by Active Shape and Statistical Models,” Pattern Recognit., vol. 48, no. 11,
pp. 3371–3384, 2015.
[11] J. A. Dargham, A. Chekima, and M. Hamdan, “Hybrid Component-Based Face Recognition System,” Distrib.
Comput. Artif. Intell. AISC, no. 151, pp. 573–574, 2012.
[12] Q. Y. Li and H. Y. Quan, “The Dimension Reduction Method of Face Feature Parameters Based on Modular
2DPCA and PCA”, Applied Mechanics and Materials, Vols. 687-691, pp. 4037-4041, 2014
[13] K. D. Kadam, “Face Recognition using Principal Component Analysis with DCT,” Int. J. Eng. Res. Gen. Sci., vol.
2, no. 4, pp. 276–280, 2014.
[14] S. Fernandes and J. Bala, “Performance Analysis of PCA-based and LDA-based Algorithms for Face Recognition,”
Int. J. Signal Process. Syst., vol. 1, no. 1, pp. 1–6, 2013.
[15] P. Sinha, B. Balas, Y. Ostrovsky and R. Russell, "Face Recognition by Humans: Nineteen Results All Computer
Vision Researchers Should Know About," in Proceedings of the IEEE, vol. 94, no. 11, pp. 1948-1962, Nov. 2006.
[16] M. K, V. Govindarajan, S. K. V V S, and R. S, “Face Recognition using Block-Based DCT Feature Extraction,” J.
Adv. Comput. Sci. Technol., vol. 1, no. 4, pp. 266–283, 2012.
[17] W. Chen, Meng Joo Er and Shiqian Wu, "Illumination compensation and normalization for robust face recognition
using discrete cosine transform in logarithm domain," in IEEE Transactions on Systems, Man, and Cybernetics,
Part B (Cybernetics), vol. 36, no. 2, pp. 458-466, April 2006.
[18] X. Zou, J. Kittler and K. Messer, "Illumination Invariant Face Recognition: A Survey," 2007 First IEEE
International Conference on Biometrics: Theory, Applications, and Systems, Crystal City, VA, 2007, pp. 1-8.
[19] S. Bag and G. Sanyal, "An efficient face recognition approach using PCA and minimum distance classifier," 2011
International Conference on Image Information Processing, Shimla, 2011, pp. 1-6.
[20] B. Bozorgtabar, H. Azami, and F. Noorian, “Illumination invariant face recognition using fuzzy LDA and FFNN,”
J. Signal Inf. Process., vol. 2012, no. February, pp. 45–50, 2012.
[21] Guoxia Sun, Liangliang Zhang and Huiqiang Sun, "Face recognition based on symmetrical weighted PCA," 2011
International Conference on Computer Science and Service System (CSSS), Nanjing, 2011, pp. 2249-2252.
[22] F. Wu, “Face Recognition Based on Wavelet Transform and Regional Directional Weighted Local Binary Pattern,”
J. Multimed., vol. 9, no. 8, pp. 1017–1023, 2014.
[23] J. Nagi, S. K. Ahmed, and F. Nagi, “Pose Invariant Face Recognition using Hybrid DWT-DCT Frequency Features
with Support Vector Machines,” in Proceedings of the 4th International Conference Information Technology and
Multimedia, 2008, no. November, pp. 99–104.
[24] H. Imtiaz and S. A. Fattah, “a face recognition scheme using wavelet based dominant features,” Signal Image
Prosessing Int. J., vol. 2, no. 3, pp. 69–80, 2011.
BIOGRAPHIES OF AUTHORS
Raja Abdullah Raja Ahmad received the B.Eng. degree in Computer and Communication
Engineering from Universiti Malaysia Perlis, M.Sc. degree in Embedded System Design
Engineering from Universiti Malaysia Perlis.
10. ISSN: 2302-9285
Bulletin of Electr Eng and Inf, Vol. 8, No. 2, June 2019 : 541 – 550
550
M.I Ahmad received the B.Eng. degree in Electrical and Electronic Engineering from Universiti
Teknologi Malaysia, M.Sc. degree in Electronic System Design Engineering from Universiti
Sains Malaysia and Ph.D. degree from Newcastle University, Newcastle upon Tyne, UK. He is
currently a senior lecturer with the School of Computer and Communication Engineering,
Universiti Malaysia Perlis, Malaysia. His current research interests include biometric,
information fusion, image processing and pattern recognition.
Said Amirul Anwar Ab. Hamid received his PhD in Computer Engineering from Universiti Sains
Malaysia in 2014. Currently he is a senior lecturer at School of Computer and Communication
Engineering, Universiti Malaysia Perlis. His research interests include image processing and
pattern recognition. Malaysia Perlis, Malaysia. His current research interests include biometric,
information fusion, image processing and pattern recognition.