This document analyzes the invariance of transform coefficients under image rotation. It examines several rotationally invariant transforms, including the angular radial transform (ART) and polar harmonic transforms (PCT, PST, PCET). An empirical analysis is conducted on test images to identify the transform coefficients that are most robust to rotation. The robust coefficients show little change in value when the image is rotated. Face recognition is then tested using only the robust coefficients versus all coefficients. The results show recognition rate is unchanged while computation time decreases when using only the robust coefficients.
This document summarizes a proposed online framework for video stabilization that uses Speeded Up Robust Feature (SURF) detection to select stable and consistent feature points from reference frames that are then tracked across all frames. A discrete Kalman filter is used to smooth estimated motion vectors and provide predictions when feature points are missing. Motion compensation is performed to generate a stabilized video sequence free of unstable camera motion. The framework estimates global motion, separates intentional from unintentional camera motion, and fills in voids through mosaicking or inpainting to produce a complete, stabilized online video.
Image Registration using NSCT and Invariant MomentCSCJournals
Image registration is a process of matching images, which are taken at different times, from different sensors or from different view points. It is an important step for a great variety of applications such as computer vision, stereo navigation, medical image analysis, pattern recognition and watermarking applications. In this paper an improved feature point selection and matching technique for image registration is proposed. This technique is based on the ability of nonsubsampled contourlet transform (NSCT) to extract significant features irrespective of feature orientation. Then the correspondence between the extracted feature points of reference image and sensed image is achieved using Zernike moments. Feature point pairs are used for estimating the transformation parameters mapping the sensed image to the reference image. Experimental results illustrate the registration accuracy over a wide range for panning and zooming movement and also the robustness of the proposed algorithm to noise. Apart from image registration proposed method can be used for shape matching and object classification. Keywords: Image Registration, NSCT, Contourlet Transform, Zernike Moment.
An Efficient Algorithm for the Segmentation of Astronomical ImagesIOSR Journals
This document proposes an efficient algorithm for segmenting celestial objects from astronomical images. The algorithm uses multiple preprocessing steps including removing bright point sources, stationary wavelet transform, total variation denoising, and adaptive histogram equalization. Level set segmentation is then used as the key technique for segmentation. Preprocessing helps overcome issues like noise, weak object edges, and low contrast. Level set segmentation can segment objects while retaining their texture and shape information for subsequent classification. The algorithm is tested on various celestial objects and shown to effectively segment them.
This document discusses Fourier descriptors and moments which are used in object recognition and image processing. Fourier descriptors represent the boundary shape of an object using the coefficients of its Fourier transform. They are useful because they are invariant to scaling, translation, and rotation. Central moments are another type of descriptor that are translation and rotation invariant. Velocity moments describe both shape and motion over time. Moment invariants are derived from moments to be invariant to specific transformations and are commonly used in image analysis applications such as object detection.
Solution of Inverse Kinematics for SCARA Manipulator Using Adaptive Neuro-Fuz...ijsc
Solution of inverse kinematic equations is complex problem, the complexity comes from the nonlinearity of joint space and Cartesian space mapping and having multiple solution. In this work, four adaptive neurofuzzy networks ANFIS are implemented to solve the inverse kinematics of 4-DOF SCARA manipulator. The implementation of ANFIS is easy, and the simulation of it shows that it is very fast and give acceptable
error.
Medial Axis Transformation based Skeletonzation of Image Patterns using Image...IOSR Journals
1) The document discusses extracting the medial axis transform (MAT) of an image pattern using the Euclidean distance transform. The image is first converted to binary, then the Euclidean distance transform is used to compute the distance of each non-zero pixel to the closest zero pixel.
2) The medial axis transform represents the core or skeleton of an image pattern. There are different algorithms for extracting the skeleton or medial axis, including sequential and parallel algorithms. The skeleton provides a simple representation that preserves topological and size characteristics of the original shape.
3) The document provides background on medial axis transforms and different skeletonization algorithms. It then describes preparing the binary image and applying the Euclidean distance transform to extract the MAT and skeleton
Improved Characters Feature Extraction and Matching Algorithm Based on SIFTNooria Sukmaningtyas
The document describes an improved SIFT feature extraction and matching algorithm based on the MSER algorithm. It first uses MSER instead of DOG to detect maximally stable elliptical regions, increasing stability and reducing the number of features. It then divides each elliptical region into fan-shaped subregions instead of square subregions, and constructs a new SIFT descriptor using Gaussian-weighted gradient information. Experimental results showed the new algorithm has affine invariance while maintaining other properties of SIFT, making it faster and better suited for real-time image processing.
This document presents a study on medial axis transformation (MAT) based skeletonization of image patterns using image processing techniques. It discusses how the MAT of an image can be extracted by first computing the Euclidean distance transform of the binary image. Local maxima in the distance transform image correspond to the MAT. Several performance evaluation metrics for analyzing skeletonized images are also introduced, such as connectivity number, thinness measurement and sensitivity. The technique is demonstrated on sample images and results show it can effectively extract the skeleton with good computational speed.
This document summarizes a proposed online framework for video stabilization that uses Speeded Up Robust Feature (SURF) detection to select stable and consistent feature points from reference frames that are then tracked across all frames. A discrete Kalman filter is used to smooth estimated motion vectors and provide predictions when feature points are missing. Motion compensation is performed to generate a stabilized video sequence free of unstable camera motion. The framework estimates global motion, separates intentional from unintentional camera motion, and fills in voids through mosaicking or inpainting to produce a complete, stabilized online video.
Image Registration using NSCT and Invariant MomentCSCJournals
Image registration is a process of matching images, which are taken at different times, from different sensors or from different view points. It is an important step for a great variety of applications such as computer vision, stereo navigation, medical image analysis, pattern recognition and watermarking applications. In this paper an improved feature point selection and matching technique for image registration is proposed. This technique is based on the ability of nonsubsampled contourlet transform (NSCT) to extract significant features irrespective of feature orientation. Then the correspondence between the extracted feature points of reference image and sensed image is achieved using Zernike moments. Feature point pairs are used for estimating the transformation parameters mapping the sensed image to the reference image. Experimental results illustrate the registration accuracy over a wide range for panning and zooming movement and also the robustness of the proposed algorithm to noise. Apart from image registration proposed method can be used for shape matching and object classification. Keywords: Image Registration, NSCT, Contourlet Transform, Zernike Moment.
An Efficient Algorithm for the Segmentation of Astronomical ImagesIOSR Journals
This document proposes an efficient algorithm for segmenting celestial objects from astronomical images. The algorithm uses multiple preprocessing steps including removing bright point sources, stationary wavelet transform, total variation denoising, and adaptive histogram equalization. Level set segmentation is then used as the key technique for segmentation. Preprocessing helps overcome issues like noise, weak object edges, and low contrast. Level set segmentation can segment objects while retaining their texture and shape information for subsequent classification. The algorithm is tested on various celestial objects and shown to effectively segment them.
This document discusses Fourier descriptors and moments which are used in object recognition and image processing. Fourier descriptors represent the boundary shape of an object using the coefficients of its Fourier transform. They are useful because they are invariant to scaling, translation, and rotation. Central moments are another type of descriptor that are translation and rotation invariant. Velocity moments describe both shape and motion over time. Moment invariants are derived from moments to be invariant to specific transformations and are commonly used in image analysis applications such as object detection.
Solution of Inverse Kinematics for SCARA Manipulator Using Adaptive Neuro-Fuz...ijsc
Solution of inverse kinematic equations is complex problem, the complexity comes from the nonlinearity of joint space and Cartesian space mapping and having multiple solution. In this work, four adaptive neurofuzzy networks ANFIS are implemented to solve the inverse kinematics of 4-DOF SCARA manipulator. The implementation of ANFIS is easy, and the simulation of it shows that it is very fast and give acceptable
error.
Medial Axis Transformation based Skeletonzation of Image Patterns using Image...IOSR Journals
1) The document discusses extracting the medial axis transform (MAT) of an image pattern using the Euclidean distance transform. The image is first converted to binary, then the Euclidean distance transform is used to compute the distance of each non-zero pixel to the closest zero pixel.
2) The medial axis transform represents the core or skeleton of an image pattern. There are different algorithms for extracting the skeleton or medial axis, including sequential and parallel algorithms. The skeleton provides a simple representation that preserves topological and size characteristics of the original shape.
3) The document provides background on medial axis transforms and different skeletonization algorithms. It then describes preparing the binary image and applying the Euclidean distance transform to extract the MAT and skeleton
Improved Characters Feature Extraction and Matching Algorithm Based on SIFTNooria Sukmaningtyas
The document describes an improved SIFT feature extraction and matching algorithm based on the MSER algorithm. It first uses MSER instead of DOG to detect maximally stable elliptical regions, increasing stability and reducing the number of features. It then divides each elliptical region into fan-shaped subregions instead of square subregions, and constructs a new SIFT descriptor using Gaussian-weighted gradient information. Experimental results showed the new algorithm has affine invariance while maintaining other properties of SIFT, making it faster and better suited for real-time image processing.
This document presents a study on medial axis transformation (MAT) based skeletonization of image patterns using image processing techniques. It discusses how the MAT of an image can be extracted by first computing the Euclidean distance transform of the binary image. Local maxima in the distance transform image correspond to the MAT. Several performance evaluation metrics for analyzing skeletonized images are also introduced, such as connectivity number, thinness measurement and sensitivity. The technique is demonstrated on sample images and results show it can effectively extract the skeleton with good computational speed.
ANALYSIS OF INTEREST POINTS OF CURVELET COEFFICIENTS CONTRIBUTIONS OF MICROS...sipij
This paper focuses on improved edge model based on Curvelet coefficients analysis. Curvelet transform is
a powerful tool for multiresolution representation of object with anisotropic edge. Curvelet coefficients
contributions have been analyzed using Scale Invariant Feature Transform (SIFT), commonly used to study
local structure in images. The permutation of Curvelet coefficients from original image and edges image
obtained from gradient operator is used to improve original edges. Experimental results show that this
method brings out details on edges when the decomposition scale increases.
Dynamic texture based traffic vehicle monitoring systemeSAT Journals
Abstract Dynamic Textures are function of both space and time which exhibit spatio-temporal stationary property. They have spatially repetitive patterns which vary with time. In this paper, importance of phase spectrum in the signals is utilized and a novel method for vehicle monitoring is proposed with the help of Fourier analysis, synthesis and image processing. Methods like Doppler radar or GPS navigation are used commonly for tracking. The proposed image based approach has an added advantage that the clear image of the object (vehicle) can be used for future reference like proof of incidence, identification of owner and registration number. Keywords-Fourier Transform, dynamic texture, phase spectrum
4 satellite image fusion using fast discreteAlok Padole
This document proposes a new satellite image fusion method using Fast Discrete Curvelet Transforms (FDCT) that aims to generate high resolution multispectral images while retaining both rich spatial and spectral details. The method defines a fusion rule based on local magnitude ratio in the FDCT domain to inject high frequency details from a high resolution panchromatic image into lower resolution multispectral bands. Experimental results on Resourcesat-1 LISS IV and Cartosat-1 images show the proposed FDCT fusion method spatially outperforms wavelet, PCA, high pass filtering, IHS, and Gram-Schmidt fusion methods based on entropy and QAB/F metrics.
This document summarizes a cylindrical robot simulation software developed for educational purposes. The software includes modules for direct and inverse kinematics, trajectory planning, and PID-computed torque control. It was created using Matlab and incorporates visual animations. Students found it helpful for understanding fundamental robot mechanics concepts.
Palmprint verification using lagrangian decomposition and invariant interestDakshina Kisku
This document summarizes a research paper on palmprint verification using Lagrangian decomposition and invariant interest points. The paper proposes a system that extracts the region of interest from palm images, uses SIFT to extract invariant features, and performs matching using a Lagrangian graph technique. It tests the system on two databases, achieving recognition rates of 97.1% and 95.8% with low false acceptance and rejection rates. The paper concludes the proposed system is effective and robust for palmprint authentication.
A reliable gait features are required to extract the gait sequences from an images. In this paper suggested a
simple method for gait identification which is based on moments. Moment values are extracted on different
number of frames of Gray Scale and Silhouette images of CASIA database. These moment values are
considered as feature values. Fuzzy logic and Nearest Neighbor Classifier are used for classification. Both
achieved higher recognition.
ABSTRACT : Image registration is an important and fundamental task in image processing used to match two different images. Image registration estimates the parameters of the geometrical transformation model that maps the sensed images back to its reference image. A Feature-Based Approach to automated image-to-image registration is presented. In this paper, various methods are used in different Phases of Image registration. The characteristics of this approach is it combines scale interaction of Discrete wavelets for feature extraction, Scale Invariant Feature Transform (SIFT) for feature matching. Scale-invariant feature transform (or SIFT) is an algorithm in computer vision to detect and describe local features in images. SIFT feature descriptor is invariant to uniform scaling, orientation, and partially invariant to affine distortion and illumination changes.
The document presents a digital image stabilization (DIS) technique based on the Hilbert-Huang transform (HHT). The technique has three main steps: (1) estimating local motion vectors (LMVs) in an image sequence, (2) using empirical mode decomposition (EMD) as part of HHT to decompose the LMV signals into intrinsic mode functions (IMFs), and (3) estimating jitter motion vectors from the IMFs to remove unwanted shaking from the image sequence. The technique is tested on three image sequences, with the LMV and IMF results presented. The HHT-based DIS method effectively separates camera intentional motion from unwanted jitter motion for stabilized video.
Gait Based Person Recognition Using Partial Least Squares Selection Scheme ijcisjournal
The document summarizes a research paper on gait-based person recognition using partial least squares selection. It presents an Arbitrary View Transformation Model (AVTM) that uses gait energy images and partial least squares (PLS) feature selection to improve gait recognition accuracy under varying viewing angles, clothing, and other conditions. The proposed AVTM PLS method is evaluated on the CASIA gait database and shown to achieve higher recognition rates compared to other existing methods, especially when there are changes in viewing angle, clothing, or whether the person is carrying something. Tables of results demonstrate the proposed method outperforms alternatives across different test conditions and ranges of gallery and probe viewing angles.
View and illumination invariant iterative based image matchingeSAT Journals
This document presents a view and illumination invariant iterative image matching method. It begins by discussing the challenges of local feature-based image matching when there are variations in view and illumination between images. It then proposes an iterative algorithm to estimate the relationship between the relative view and illumination of images, transform one image to match the other's view and illumination, and improve matching accuracy. Key aspects of the algorithm include iteratively estimating the homography matrix H and histogram transformation L to model the view and illumination changes between images. The algorithm is shown to significantly improve matching performance compared to traditional detectors by making matching more robust to changes in view and illumination.
Analysis of Image Super-Resolution via Reconstruction Filters for Pure Transl...CSCJournals
In this work, a special case of the image super-resolution problem where the only type of motion is global translational motion and the blurs are shift-invariant is investigated. The necessary conditions for exact reconstruction of the original image by using finite impulse-response reconstruction filters are investigated and determined. If the number of available low-resolution images is larger than a threshold and the blur functions meet a certain property, a reconstruction filter set for perfect image super-resolution can be generated even in the absence of motion. Given that the conditions are satisfied, a method for exact super-resolution is presented to validate the analysis results and it is shown that for the fully determined case, perfect reconstruction of the original image is achieved. Finally, some realistic conditions that make the super-resolution problem ill-posed are treated and their effects on exact super-resolution are discussed.
Feature selection is the fundamental step in image
registration. Various tasks such as feature extraction, detection
are based on feature based approach. In the current paper we are
going to discuss about our technique that is hybrid of Local affine
and thin plate spline. An automatic edge detection method to
achieve the correct edge map is put forward to dealing with
image registration with affine transformation for the better
image registration. Registration algorithms compute
transformations to set correspondence between the two images.
The purpose of this paper is to provide a comprehensive
comparison of the existing literature available on Image
registration methods with proposed technique
This project is to retrieve the similar geographic images from the dataset based on the features extracted.
Retrieval is the process of collecting the relevant images from the dataset which contains more number of
images. Initially the preprocessing step is performed in order to remove noise occurred in input image with
the help of Gaussian filter. As the second step, Gray Level Co-occurrence Matrix (GLCM), Scale Invariant
Feature Transform (SIFT), and Moment Invariant Feature algorithms are implemented to extract the
features from the images. After this process, the relevant geographic images are retrieved from the dataset
by using Euclidean distance. In this, the dataset consists of totally 40 images. From that the images which
are all related to the input image are retrieved by using Euclidean distance. The approach of SIFT is to
perform reliable recognition, it is important that the feature extracted from the training image be
detectable even under changes in image scale, noise and illumination. The GLCM calculates how often a
pixel with gray level value occurs. While the focus is on image retrieval, our project is effectively used in
the applications such as detection and classification.
This document discusses using Poisson's equation to extract features from human actions represented as space-time shapes. It begins by introducing how human actions can be represented as 3D shapes formed by concatenating 2D silhouettes over time. It then discusses how solving Poisson's equation on these space-time shapes allows extracting useful features like local space-time saliency, orientation, and dynamics. These features capture properties of the pose and motion of body parts and are shown to be effective for tasks like action recognition and clustering. The method is fast, applicable in many scenarios, and robust to issues like occlusions and scale/viewpoint changes.
FAN search for image copy-move forgery-amalta 2014SondosFadl
1) The document proposes a fast fan search method for detecting copy-move image forgery. It divides images into blocks, extracts features from blocks, and uses a fan search algorithm to detect duplicated blocks more efficiently than previous methods.
2) Experimental results show the proposed method can detect copy-move forgery 75% faster than other methods, with 99% precision and 98% recall.
3) Future work will improve the method to detect duplications under geometric transformations like rotation and scaling.
ADAPTIVE, SCALABLE, TRANSFORMDOMAIN GLOBAL MOTION ESTIMATION FOR VIDEO STABIL...cscpconf
Video Stabilization, which is important for better analysis and user experience, is typically done through Global Motion Estimation (GME) and Compensation. GME can be done in image domain using many techniques or in Transform domain using the well-known Phase Correlation methods which relate motion to phase shift in the spectrum. While image domain methods are generally slower (due to dense vector field computations), they can do global as well as local motion estimation. Transform domain methods cannot normally do local motion, but are faster and more accurate on homogeneous images, and are resilient to even rapid illumination changes and large motion. However both these approaches can become very time consuming if one needs more accuracy and smoothness because of the nature of the tradeoff. We show here that wavelet transforms can be used in a novel way to achieve a very smooth stabilization along with a significant speedup in this Fourier domain computation without sacrificing accuracy. We
do this by adaptively selecting and combining motion computed on a specific pair of sub-bands using the wavelet interpolation capability. Our approach yields a smooth, scalable, fast and
adaptive algorithm (based on time requirement and recent motion history) to yield significantly better accuracy than a single level wavelet decomposition based approach.
Medical image analysis and processing using a dual transformeSAT Journals
Abstract The demand for images in medical field has increased drastically over the years. The need for reducing the storage space has resulted in image compression. This paper presents a dual transform for medical image compression algorithm. The experimental results determines how the compression ratio (CR), peak signal to noise ratio (PSNR) and SNR (signal to noise ratio) of different compression algorithms responds to dual transform algorithm. Keywords: DCT, SPIHT, Haar Wavelet, Linear approximation transform, image compression, Singular Value Decomposition (SVD).
This document presents a paper that proposes an image registration algorithm using log-polar transform and FFT-based correlation. The algorithm first estimates the angle, scale, and translation between two images by converting them to the log-polar domain, where rotation and scaling appear as translation. It then recovers the residual translation using gradient correlation in the spatial domain. The algorithm is tested on various images related by similarity transformations and is shown to accurately recover scales up to 5.85 times while being robust to noise. It provides a computationally efficient way to register images using properties of the Fourier transform and log-polar mappings.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
An automatic algorithm for object recognition and detection based on asift ke...Kunal Kishor Nirala
This document presents an automatic algorithm for object recognition and detection based on ASIFT keypoints. The algorithm combines affine scale invariant feature transform (ASIFT) and a region merging algorithm. ASIFT is used to extract keypoints from a training image of the object. These keypoints are then used instead of user markers in a region merging algorithm to recognize and detect the object with full boundary in other images. Experimental results show the method is efficient and accurate at recognizing and detecting objects.
ANALYSIS OF INTEREST POINTS OF CURVELET COEFFICIENTS CONTRIBUTIONS OF MICROS...sipij
This paper focuses on improved edge model based on Curvelet coefficients analysis. Curvelet transform is
a powerful tool for multiresolution representation of object with anisotropic edge. Curvelet coefficients
contributions have been analyzed using Scale Invariant Feature Transform (SIFT), commonly used to study
local structure in images. The permutation of Curvelet coefficients from original image and edges image
obtained from gradient operator is used to improve original edges. Experimental results show that this
method brings out details on edges when the decomposition scale increases.
Dynamic texture based traffic vehicle monitoring systemeSAT Journals
Abstract Dynamic Textures are function of both space and time which exhibit spatio-temporal stationary property. They have spatially repetitive patterns which vary with time. In this paper, importance of phase spectrum in the signals is utilized and a novel method for vehicle monitoring is proposed with the help of Fourier analysis, synthesis and image processing. Methods like Doppler radar or GPS navigation are used commonly for tracking. The proposed image based approach has an added advantage that the clear image of the object (vehicle) can be used for future reference like proof of incidence, identification of owner and registration number. Keywords-Fourier Transform, dynamic texture, phase spectrum
4 satellite image fusion using fast discreteAlok Padole
This document proposes a new satellite image fusion method using Fast Discrete Curvelet Transforms (FDCT) that aims to generate high resolution multispectral images while retaining both rich spatial and spectral details. The method defines a fusion rule based on local magnitude ratio in the FDCT domain to inject high frequency details from a high resolution panchromatic image into lower resolution multispectral bands. Experimental results on Resourcesat-1 LISS IV and Cartosat-1 images show the proposed FDCT fusion method spatially outperforms wavelet, PCA, high pass filtering, IHS, and Gram-Schmidt fusion methods based on entropy and QAB/F metrics.
This document summarizes a cylindrical robot simulation software developed for educational purposes. The software includes modules for direct and inverse kinematics, trajectory planning, and PID-computed torque control. It was created using Matlab and incorporates visual animations. Students found it helpful for understanding fundamental robot mechanics concepts.
Palmprint verification using lagrangian decomposition and invariant interestDakshina Kisku
This document summarizes a research paper on palmprint verification using Lagrangian decomposition and invariant interest points. The paper proposes a system that extracts the region of interest from palm images, uses SIFT to extract invariant features, and performs matching using a Lagrangian graph technique. It tests the system on two databases, achieving recognition rates of 97.1% and 95.8% with low false acceptance and rejection rates. The paper concludes the proposed system is effective and robust for palmprint authentication.
A reliable gait features are required to extract the gait sequences from an images. In this paper suggested a
simple method for gait identification which is based on moments. Moment values are extracted on different
number of frames of Gray Scale and Silhouette images of CASIA database. These moment values are
considered as feature values. Fuzzy logic and Nearest Neighbor Classifier are used for classification. Both
achieved higher recognition.
ABSTRACT : Image registration is an important and fundamental task in image processing used to match two different images. Image registration estimates the parameters of the geometrical transformation model that maps the sensed images back to its reference image. A Feature-Based Approach to automated image-to-image registration is presented. In this paper, various methods are used in different Phases of Image registration. The characteristics of this approach is it combines scale interaction of Discrete wavelets for feature extraction, Scale Invariant Feature Transform (SIFT) for feature matching. Scale-invariant feature transform (or SIFT) is an algorithm in computer vision to detect and describe local features in images. SIFT feature descriptor is invariant to uniform scaling, orientation, and partially invariant to affine distortion and illumination changes.
The document presents a digital image stabilization (DIS) technique based on the Hilbert-Huang transform (HHT). The technique has three main steps: (1) estimating local motion vectors (LMVs) in an image sequence, (2) using empirical mode decomposition (EMD) as part of HHT to decompose the LMV signals into intrinsic mode functions (IMFs), and (3) estimating jitter motion vectors from the IMFs to remove unwanted shaking from the image sequence. The technique is tested on three image sequences, with the LMV and IMF results presented. The HHT-based DIS method effectively separates camera intentional motion from unwanted jitter motion for stabilized video.
Gait Based Person Recognition Using Partial Least Squares Selection Scheme ijcisjournal
The document summarizes a research paper on gait-based person recognition using partial least squares selection. It presents an Arbitrary View Transformation Model (AVTM) that uses gait energy images and partial least squares (PLS) feature selection to improve gait recognition accuracy under varying viewing angles, clothing, and other conditions. The proposed AVTM PLS method is evaluated on the CASIA gait database and shown to achieve higher recognition rates compared to other existing methods, especially when there are changes in viewing angle, clothing, or whether the person is carrying something. Tables of results demonstrate the proposed method outperforms alternatives across different test conditions and ranges of gallery and probe viewing angles.
View and illumination invariant iterative based image matchingeSAT Journals
This document presents a view and illumination invariant iterative image matching method. It begins by discussing the challenges of local feature-based image matching when there are variations in view and illumination between images. It then proposes an iterative algorithm to estimate the relationship between the relative view and illumination of images, transform one image to match the other's view and illumination, and improve matching accuracy. Key aspects of the algorithm include iteratively estimating the homography matrix H and histogram transformation L to model the view and illumination changes between images. The algorithm is shown to significantly improve matching performance compared to traditional detectors by making matching more robust to changes in view and illumination.
Analysis of Image Super-Resolution via Reconstruction Filters for Pure Transl...CSCJournals
In this work, a special case of the image super-resolution problem where the only type of motion is global translational motion and the blurs are shift-invariant is investigated. The necessary conditions for exact reconstruction of the original image by using finite impulse-response reconstruction filters are investigated and determined. If the number of available low-resolution images is larger than a threshold and the blur functions meet a certain property, a reconstruction filter set for perfect image super-resolution can be generated even in the absence of motion. Given that the conditions are satisfied, a method for exact super-resolution is presented to validate the analysis results and it is shown that for the fully determined case, perfect reconstruction of the original image is achieved. Finally, some realistic conditions that make the super-resolution problem ill-posed are treated and their effects on exact super-resolution are discussed.
Feature selection is the fundamental step in image
registration. Various tasks such as feature extraction, detection
are based on feature based approach. In the current paper we are
going to discuss about our technique that is hybrid of Local affine
and thin plate spline. An automatic edge detection method to
achieve the correct edge map is put forward to dealing with
image registration with affine transformation for the better
image registration. Registration algorithms compute
transformations to set correspondence between the two images.
The purpose of this paper is to provide a comprehensive
comparison of the existing literature available on Image
registration methods with proposed technique
This project is to retrieve the similar geographic images from the dataset based on the features extracted.
Retrieval is the process of collecting the relevant images from the dataset which contains more number of
images. Initially the preprocessing step is performed in order to remove noise occurred in input image with
the help of Gaussian filter. As the second step, Gray Level Co-occurrence Matrix (GLCM), Scale Invariant
Feature Transform (SIFT), and Moment Invariant Feature algorithms are implemented to extract the
features from the images. After this process, the relevant geographic images are retrieved from the dataset
by using Euclidean distance. In this, the dataset consists of totally 40 images. From that the images which
are all related to the input image are retrieved by using Euclidean distance. The approach of SIFT is to
perform reliable recognition, it is important that the feature extracted from the training image be
detectable even under changes in image scale, noise and illumination. The GLCM calculates how often a
pixel with gray level value occurs. While the focus is on image retrieval, our project is effectively used in
the applications such as detection and classification.
This document discusses using Poisson's equation to extract features from human actions represented as space-time shapes. It begins by introducing how human actions can be represented as 3D shapes formed by concatenating 2D silhouettes over time. It then discusses how solving Poisson's equation on these space-time shapes allows extracting useful features like local space-time saliency, orientation, and dynamics. These features capture properties of the pose and motion of body parts and are shown to be effective for tasks like action recognition and clustering. The method is fast, applicable in many scenarios, and robust to issues like occlusions and scale/viewpoint changes.
FAN search for image copy-move forgery-amalta 2014SondosFadl
1) The document proposes a fast fan search method for detecting copy-move image forgery. It divides images into blocks, extracts features from blocks, and uses a fan search algorithm to detect duplicated blocks more efficiently than previous methods.
2) Experimental results show the proposed method can detect copy-move forgery 75% faster than other methods, with 99% precision and 98% recall.
3) Future work will improve the method to detect duplications under geometric transformations like rotation and scaling.
ADAPTIVE, SCALABLE, TRANSFORMDOMAIN GLOBAL MOTION ESTIMATION FOR VIDEO STABIL...cscpconf
Video Stabilization, which is important for better analysis and user experience, is typically done through Global Motion Estimation (GME) and Compensation. GME can be done in image domain using many techniques or in Transform domain using the well-known Phase Correlation methods which relate motion to phase shift in the spectrum. While image domain methods are generally slower (due to dense vector field computations), they can do global as well as local motion estimation. Transform domain methods cannot normally do local motion, but are faster and more accurate on homogeneous images, and are resilient to even rapid illumination changes and large motion. However both these approaches can become very time consuming if one needs more accuracy and smoothness because of the nature of the tradeoff. We show here that wavelet transforms can be used in a novel way to achieve a very smooth stabilization along with a significant speedup in this Fourier domain computation without sacrificing accuracy. We
do this by adaptively selecting and combining motion computed on a specific pair of sub-bands using the wavelet interpolation capability. Our approach yields a smooth, scalable, fast and
adaptive algorithm (based on time requirement and recent motion history) to yield significantly better accuracy than a single level wavelet decomposition based approach.
Medical image analysis and processing using a dual transformeSAT Journals
Abstract The demand for images in medical field has increased drastically over the years. The need for reducing the storage space has resulted in image compression. This paper presents a dual transform for medical image compression algorithm. The experimental results determines how the compression ratio (CR), peak signal to noise ratio (PSNR) and SNR (signal to noise ratio) of different compression algorithms responds to dual transform algorithm. Keywords: DCT, SPIHT, Haar Wavelet, Linear approximation transform, image compression, Singular Value Decomposition (SVD).
This document presents a paper that proposes an image registration algorithm using log-polar transform and FFT-based correlation. The algorithm first estimates the angle, scale, and translation between two images by converting them to the log-polar domain, where rotation and scaling appear as translation. It then recovers the residual translation using gradient correlation in the spatial domain. The algorithm is tested on various images related by similarity transformations and is shown to accurately recover scales up to 5.85 times while being robust to noise. It provides a computationally efficient way to register images using properties of the Fourier transform and log-polar mappings.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
An automatic algorithm for object recognition and detection based on asift ke...Kunal Kishor Nirala
This document presents an automatic algorithm for object recognition and detection based on ASIFT keypoints. The algorithm combines affine scale invariant feature transform (ASIFT) and a region merging algorithm. ASIFT is used to extract keypoints from a training image of the object. These keypoints are then used instead of user markers in a region merging algorithm to recognize and detect the object with full boundary in other images. Experimental results show the method is efficient and accurate at recognizing and detecting objects.
This document summarizes a research paper on encrypting images using wavelet transforms and chaotic maps. It begins with an abstract that describes using discrete wavelet transforms and calculating metrics like number of changing pixel rate and unified averaged changed intensity to evaluate encryption strength. It then provides background on image processing techniques, discrete wavelet transforms, and logistic maps. The proposed method segments the original image into blocks, encrypts each block by applying a discrete wavelet transform and using a logistic map to generate random numbers for permutation. Encryption involves conversion to 1D, permutation, and inverse conversion. Decryption reverses the process. Results are evaluated using NPCR and UACI metrics between the encrypted image and a changed pixel key image.
Solution of Inverse Kinematics for SCARA Manipulator Using Adaptive Neuro-Fuz...ijsc
Solution of inverse kinematic equations is complex problem, the complexity comes from the nonlinearity of joint space and Cartesian space mapping and having multiple solution. In this work, four adaptive neurofuzzy networks ANFIS are implemented to solve the inverse kinematics of 4-DOF SCARA manipulator. The implementation of ANFIS is easy, and the simulation of it shows that it is very fast and give acceptable error.
Sliced Ridgelet Transform for Image DenoisingIOSR Journals
This document discusses using a sliced ridgelet transform for image denoising. It begins with an introduction to ridgelet transforms and their effectiveness for image denoising compared to wavelet transforms. It then describes the proposed method which computes ridgelet transforms on slices of the noisy image to denoise each slice. After applying an inverse ridgelet transform, a Wiener filter is used to further improve the results by reducing blurring while preserving edges. Experimental results show the adaptive Wiener filter produces better results than linear filtering for denoising while maintaining high-frequency image components like edges.
The document discusses using triangular basis functions for image transforms and compression. It proposes that triangular waveforms can be used as non-sinusoidal orthogonal basis functions for image transforms. The key steps include: (1) deriving the triangular basis functions from orthogonal matrices of different sizes, (2) using the basis functions to decompose images into frequency components through triangular transforms, (3) compressing images by selecting and quantizing the lowest frequency components obtained from the transforms. The approach allows for reconstructing damaged images by recalculating values using the derived basis functions.
Review on Medical Image Fusion using Shearlet TransformIRJET Journal
This document reviews medical image fusion using the shearlet transform. It discusses how medical image fusion combines information from multimodality images like CT, MRI, PET into a single image. The shearlet transform allows for more efficient encoding of anisotropic features compared to wavelets. The proposed algorithm involves decomposing registered input images using shearlet transforms, applying fusion rules to select coefficients, and reconstructing the fused image. Medical image fusion using shearlets can improve diagnosis by combining complementary anatomical and functional details from different imaging modalities.
Forward and Inverse Kinematic Analysis of Robotic ManipulatorsIRJET Journal
The document discusses forward and inverse kinematic analysis of 5 DOF and 6 DOF robotic manipulators. It presents the Denavit-Hartenberg parameters to model the link lengths, twist angles, offsets etc. of the manipulators. Forward kinematics is used to calculate the position and orientation of the end effector given the joint angles, while inverse kinematics is used to determine the required joint angles to achieve a desired end effector pose. Results for a 5 DOF manipulator using forward and inverse kinematic equations are presented.
International Journal of Computational Engineering Research(IJCER) is an intentional online Journal in English monthly publishing journal. This Journal publish original research work that contributes significantly to further the scientific knowledge in engineering and Technology.
This document describes a hybrid technique for image enhancement that uses both frequency domain and spatial domain techniques. It begins with applying frequency domain techniques like discrete cosine transform (DCT) or discrete wavelet transform (DWT) to separate an image into magnitude and phase spectra. The magnitude is then enhanced before recombining it with the phase using inverse DCT/DWT. Spatial domain techniques like power law or log transforms are then applied to further enhance contrast and brightness. The technique is evaluated on sample images and shown to achieve better PSNR and lower MSE than frequency domain techniques alone. In conclusion, combining frequency and spatial domain methods provides an effective approach for image enhancement.
Forward and Inverse Kinematic Analysis of Robotic ManipulatorsIRJET Journal
The document discusses forward and inverse kinematic analysis of 5 DOF and 6 DOF robotic manipulators. It presents the Denavit-Hartenberg (DH) parameter modeling approach to determine the homogeneous transformation matrices between links to solve the forward kinematics. The inverse kinematics is solved by multiplying the inverse of the transformation matrices and equating the end effector positions and orientations. Results for 5 DOF manipulator show the joint values that provide different end effector positions and orientations.
Inverse Kinematics Analysis for Manipulator Robot with Wrist Offset Based On ...Waqas Tariq
This paper presents an algorithm to solve the inverse kinematics for a six degree of freedom (6 DOF) manipulator robot with wrist offset. This type of robot has a complex inverse kinematics, which needs a long time for such calculation. The proposed algorithm starts from find the wrist point by vectors computation then compute the first three joint angles and after that compute the wrist angles by analytic solution. This algorithm is tested for the TQ MA2000 manipulator robot as case study. The obtained results was compared with results of rotational vector algorithm where both algorithms have the same accuracy but the proposed algorithm saving round about 99.6% of the computation time required by the rotational vector algorithm, which leads to used this algorithm in real time robot control.
11.similarity of inference face matching on angle orientedAlexander Decker
This document presents a new angle-oriented face recognition algorithm that uses discrete cosine transform (DCT). The algorithm first normalizes input faces by rotating them to match the pose of database faces if needed. It then extracts features from the faces using DCT and compares them using Euclidean distance or cosine similarity measures. Experimental results show the proposed algorithm achieves 92-98% recognition rates, outperforming existing Karhunen-Loeve transform methods. The algorithm increases reliability of face detection compared to threshold-based approaches and is well-suited for applications like security and biometrics.
Similarity of inference face matching on angle orientedAlexander Decker
This document summarizes a research paper on angle oriented face recognition using discrete cosine transforms (DCT).
[1] It proposes an algorithm that first normalizes input faces for size and angle to match a database, then extracts local features using DCT and normalization techniques.
[2] DCT is discussed as it closely approximates the optimal Karhunen-Loeve transform while being computationally efficient. Similarity matching is done using Euclidean distance or cosine similarity measures.
[3] The basic algorithm involves face normalization, DCT feature extraction, and recognition by comparing features to the database. Experimental results showed the proposed approach led to more reliable detection than threshold-based methods.
This document presents a dual transform method for medical image compression that uses both singular value decomposition (SVD) and Haar wavelet transform. It compares the proposed dual transform method to existing Haar wavelet-SPIHT and DCT-SPIHT compression methods on 3 medical images. The dual transform method achieved higher compression ratios and PSNR values at 0.4 bits per pixel compared to the other methods, indicating better preservation of image quality at higher compression. The dual transform is thus concluded to be suitable for compressing medical images where no deterioration of image quality is acceptable.
Action Trajectory Reconstruction for Controlling of Vehicle Using SensorsIOSR Journals
Abstract: Inertial sensors, such as accelerometers and gyro-scopes, are rarely used by themselves to compute
velocity and position as each requires the integration of very noisy data. The variance and bias in the resulting
position and velocity estimates grow un-bounded in time. This paper proposes a solution to provide a de-biased
and de-noised estimation of position and velocity of moving vehicle actions from accelerometer measurements.
The method uses a continuous wavelet transform applied to the measurements recursively to provide reliable
action trajectory reconstruction. The results are presented from experiments performed with a MEMS accelerometer
and gyroscope.
Keywords: Action trajectory, continuous wavelet transform, inertial measurement unit.
Mask R-CNN extends Faster R-CNN by adding a branch for predicting segmentation masks in parallel with bounding box recognition and classification. It introduces a new layer called RoIAlign to address misalignment issues in the RoIPool layer of Faster R-CNN. RoIAlign improves mask accuracy by 10-50% by removing quantization and properly aligning extracted features. Mask R-CNN runs at 5fps with only a small overhead compared to Faster R-CNN.
This document summarizes a research paper on fingerprint verification using steerable filters. It discusses how existing fingerprint recognition systems rely on minutiae matching but have limitations related to image quality and minutiae extraction. The paper proposes using steerable filters to extract texture features from fingerprints. Steerable filters can selectively detect texture orientations and frequencies. The method applies steerable filters at different orientations to a fingerprint image to extract features, divides the image into blocks, and computes mean values to form a feature matrix for classification. Experimental results on two databases achieved a genuine acceptance rate of 94% for verification.
This document summarizes a research paper on fingerprint verification using steerable filters. It discusses how steerable filters can be used to extract texture features from fingerprints, without requiring minutiae extraction. The key points are:
1) A set of steerable filters at different orientations are applied to the fingerprint image to extract texture features.
2) The fingerprint image is divided into blocks and the mean response of each block for each filter provides the feature vector.
3) Experiments on two fingerprint databases achieved a genuine acceptance rate of 94% for verification.
4) The method extracts features directly from the image, without pre-processing steps required for minutiae-based matching, and with fewer computations.
Similar to Empirical Analysis of Invariance of Transform Coefficients under Rotation (20)
A Novel Method for Prevention of Bandwidth Distributed Denial of Service AttacksIJERD Editor
Distributed Denial of Service (DDoS) Attacks became a massive threat to the Internet. Traditional
Architecture of internet is vulnerable to the attacks like DDoS. Attacker primarily acquire his army of Zombies,
then that army will be instructed by the Attacker that when to start an attack and on whom the attack should be
done. In this paper, different techniques which are used to perform DDoS Attacks, Tools that were used to
perform Attacks and Countermeasures in order to detect the attackers and eliminate the Bandwidth Distributed
Denial of Service attacks (B-DDoS) are reviewed. DDoS Attacks were done by using various Flooding
techniques which are used in DDoS attack.
The main purpose of this paper is to design an architecture which can reduce the Bandwidth
Distributed Denial of service Attack and make the victim site or server available for the normal users by
eliminating the zombie machines. Our Primary focus of this paper is to dispute how normal machines are
turning into zombies (Bots), how attack is been initiated, DDoS attack procedure and how an organization can
save their server from being a DDoS victim. In order to present this we implemented a simulated environment
with Cisco switches, Routers, Firewall, some virtual machines and some Attack tools to display a real DDoS
attack. By using Time scheduling, Resource Limiting, System log, Access Control List and some Modular
policy Framework we stopped the attack and identified the Attacker (Bot) machines
Hearing loss is one of the most common human impairments. It is estimated that by year 2015 more
than 700 million people will suffer mild deafness. Most can be helped by hearing aid devices depending on the
severity of their hearing loss. This paper describes the implementation and characterization details of a dual
channel transmitter front end (TFE) for digital hearing aid (DHA) applications that use novel micro
electromechanical- systems (MEMS) audio transducers and ultra-low power-scalable analog-to-digital
converters (ADCs), which enable a very-low form factor, energy-efficient implementation for next-generation
DHA. The contribution of the design is the implementation of the dual channel MEMS microphones and powerscalable
ADC system.
Influence of tensile behaviour of slab on the structural Behaviour of shear c...IJERD Editor
-A composite beam is composed of a steel beam and a slab connected by means of shear connectors
like studs installed on the top flange of the steel beam to form a structure behaving monolithically. This study
analyzes the effects of the tensile behavior of the slab on the structural behavior of the shear connection like slip
stiffness and maximum shear force in composite beams subjected to hogging moment. The results show that the
shear studs located in the crack-concentration zones due to large hogging moments sustain significantly smaller
shear force and slip stiffness than the other zones. Moreover, the reduction of the slip stiffness in the shear
connection appears also to be closely related to the change in the tensile strain of rebar according to the increase
of the load. Further experimental and analytical studies shall be conducted considering variables such as the
reinforcement ratio and the arrangement of shear connectors to achieve efficient design of the shear connection
in composite beams subjected to hogging moment.
Gold prospecting using Remote Sensing ‘A case study of Sudan’IJERD Editor
Gold has been extracted from northeast Africa for more than 5000 years, and this may be the first
place where the metal was extracted. The Arabian-Nubian Shield (ANS) is an exposure of Precambrian
crystalline rocks on the flanks of the Red Sea. The crystalline rocks are mostly Neoproterozoic in age. ANS
includes the nations of Israel, Jordan. Egypt, Saudi Arabia, Sudan, Eritrea, Ethiopia, Yemen, and Somalia.
Arabian Nubian Shield Consists of juvenile continental crest that formed between 900 550 Ma, when intra
oceanic arc welded together along ophiolite decorated arc. Primary Au mineralization probably developed in
association with the growth of intra oceanic arc and evolution of back arc. Multiple episodes of deformation
have obscured the primary metallogenic setting, but at least some of the deposits preserve evidence that they
originate as sea floor massive sulphide deposits.
The Red Sea Hills Region is a vast span of rugged, harsh and inhospitable sector of the Earth with
inimical moon-like terrain, nevertheless since ancient times it is famed to be an abode of gold and was a major
source of wealth for the Pharaohs of ancient Egypt. The Pharaohs old workings have been periodically
rediscovered through time. Recent endeavours by the Geological Research Authority of Sudan led to the
discovery of a score of occurrences with gold and massive sulphide mineralizations. In the nineties of the
previous century the Geological Research Authority of Sudan (GRAS) in cooperation with BRGM utilized
satellite data of Landsat TM using spectral ratio technique to map possible mineralized zones in the Red Sea
Hills of Sudan. The outcome of the study mapped a gossan type gold mineralization. Band ratio technique was
applied to Arbaat area and a signature of alteration zone was detected. The alteration zones are commonly
associated with mineralization. The alteration zones are commonly associated with mineralization. A filed check
confirmed the existence of stock work of gold bearing quartz in the alteration zone. Another type of gold
mineralization that was discovered using remote sensing is the gold associated with metachert in the Atmur
Desert.
Reducing Corrosion Rate by Welding DesignIJERD Editor
This document summarizes a study on reducing corrosion rates in steel through welding design. The researchers tested different welding groove designs (X, V, 1/2X, 1/2V) and preheating temperatures (400°C, 500°C, 600°C) on ferritic malleable iron samples. Testing found that X and V groove designs with 500°C and 600°C preheating had corrosion rates of 0.5-0.69% weight loss after 14 days, compared to 0.57-0.76% for 400°C preheating. Higher preheating reduced residual stresses which decreased corrosion. Residual stresses were 1.7 MPa for optimal X groove and 600°C
Router 1X3 – RTL Design and VerificationIJERD Editor
Routing is the process of moving a packet of data from source to destination and enables messages
to pass from one computer to another and eventually reach the target machine. A router is a networking device
that forwards data packets between computer networks. It is connected to two or more data lines from different
networks (as opposed to a network switch, which connects data lines from one single network). This paper,
mainly emphasizes upon the study of router device, it‟s top level architecture, and how various sub-modules of
router i.e. Register, FIFO, FSM and Synchronizer are synthesized, and simulated and finally connected to its top
module.
Active Power Exchange in Distributed Power-Flow Controller (DPFC) At Third Ha...IJERD Editor
This paper presents a component within the flexible ac-transmission system (FACTS) family, called
distributed power-flow controller (DPFC). The DPFC is derived from the unified power-flow controller (UPFC)
with an eliminated common dc link. The DPFC has the same control capabilities as the UPFC, which comprise
the adjustment of the line impedance, the transmission angle, and the bus voltage. The active power exchange
between the shunt and series converters, which is through the common dc link in the UPFC, is now through the
transmission lines at the third-harmonic frequency. DPFC multiple small-size single-phase converters which
reduces the cost of equipment, no voltage isolation between phases, increases redundancy and there by
reliability increases. The principle and analysis of the DPFC are presented in this paper and the corresponding
simulation results that are carried out on a scaled prototype are also shown.
Mitigation of Voltage Sag/Swell with Fuzzy Control Reduced Rating DVRIJERD Editor
Power quality has been an issue that is becoming increasingly pivotal in industrial electricity
consumers point of view in recent times. Modern industries employ Sensitive power electronic equipments,
control devices and non-linear loads as part of automated processes to increase energy efficiency and
productivity. Voltage disturbances are the most common power quality problem due to this the use of a large
numbers of sophisticated and sensitive electronic equipment in industrial systems is increased. This paper
discusses the design and simulation of dynamic voltage restorer for improvement of power quality and
reduce the harmonics distortion of sensitive loads. Power quality problem is occurring at non-standard
voltage, current and frequency. Electronic devices are very sensitive loads. In power system voltage sag,
swell, flicker and harmonics are some of the problem to the sensitive load. The compensation capability
of a DVR depends primarily on the maximum voltage injection ability and the amount of stored
energy available within the restorer. This device is connected in series with the distribution feeder at
medium voltage. A fuzzy logic control is used to produce the gate pulses for control circuit of DVR and the
circuit is simulated by using MATLAB/SIMULINK software.
Study on the Fused Deposition Modelling In Additive ManufacturingIJERD Editor
Additive manufacturing process, also popularly known as 3-D printing, is a process where a product
is created in a succession of layers. It is based on a novel materials incremental manufacturing philosophy.
Unlike conventional manufacturing processes where material is removed from a given work price to derive the
final shape of a product, 3-D printing develops the product from scratch thus obviating the necessity to cut away
materials. This prevents wastage of raw materials. Commonly used raw materials for the process are ABS
plastic, PLA and nylon. Recently the use of gold, bronze and wood has also been implemented. The complexity
factor of this process is 0% as in any object of any shape and size can be manufactured.
Spyware triggering system by particular string valueIJERD Editor
This computer programme can be used for good and bad purpose in hacking or in any general
purpose. We can say it is next step for hacking techniques such as keylogger and spyware. Once in this system if
user or hacker store particular string as a input after that software continually compare typing activity of user
with that stored string and if it is match then launch spyware programme.
A Blind Steganalysis on JPEG Gray Level Image Based on Statistical Features a...IJERD Editor
This paper presents a blind steganalysis technique to effectively attack the JPEG steganographic
schemes i.e. Jsteg, F5, Outguess and DWT Based. The proposed method exploits the correlations between
block-DCTcoefficients from intra-block and inter-block relation and the statistical moments of characteristic
functions of the test image is selected as features. The features are extracted from the BDCT JPEG 2-array.
Support Vector Machine with cross-validation is implemented for the classification.The proposed scheme gives
improved outcome in attacking.
Secure Image Transmission for Cloud Storage System Using Hybrid SchemeIJERD Editor
- Data over the cloud is transferred or transmitted between servers and users. Privacy of that
data is very important as it belongs to personal information. If data get hacked by the hacker, can be
used to defame a person’s social data. Sometimes delay are held during data transmission. i.e. Mobile
communication, bandwidth is low. Hence compression algorithms are proposed for fast and efficient
transmission, encryption is used for security purposes and blurring is used by providing additional
layers of security. These algorithms are hybridized for having a robust and efficient security and
transmission over cloud storage system.
Application of Buckley-Leverett Equation in Modeling the Radius of Invasion i...IJERD Editor
A thorough review of existing literature indicates that the Buckley-Leverett equation only analyzes
waterflood practices directly without any adjustments on real reservoir scenarios. By doing so, quite a number
of errors are introduced into these analyses. Also, for most waterflood scenarios, a radial investigation is more
appropriate than a simplified linear system. This study investigates the adoption of the Buckley-Leverett
equation to estimate the radius invasion of the displacing fluid during waterflooding. The model is also adopted
for a Microbial flood and a comparative analysis is conducted for both waterflooding and microbial flooding.
Results shown from the analysis doesn’t only records a success in determining the radial distance of the leading
edge of water during the flooding process, but also gives a clearer understanding of the applicability of
microbes to enhance oil production through in-situ production of bio-products like bio surfactans, biogenic
gases, bio acids etc.
Gesture Gaming on the World Wide Web Using an Ordinary Web CameraIJERD Editor
- Gesture gaming is a method by which users having a laptop/pc/x-box play games using natural or
bodily gestures. This paper presents a way of playing free flash games on the internet using an ordinary webcam
with the help of open source technologies. Emphasis in human activity recognition is given on the pose
estimation and the consistency in the pose of the player. These are estimated with the help of an ordinary web
camera having different resolutions from VGA to 20mps. Our work involved giving a 10 second documentary to
the user on how to play a particular game using gestures and what are the various kinds of gestures that can be
performed in front of the system. The initial inputs of the RGB values for the gesture component is obtained by
instructing the user to place his component in a red box in about 10 seconds after the short documentary before
the game is finished. Later the system opens the concerned game on the internet on popular flash game sites like
miniclip, games arcade, GameStop etc and loads the game clicking at various places and brings the state to a
place where the user is to perform only gestures to start playing the game. At any point of time the user can call
off the game by hitting the esc key and the program will release all of the controls and return to the desktop. It
was noted that the results obtained using an ordinary webcam matched that of the Kinect and the users could
relive the gaming experience of the free flash games on the net. Therefore effective in game advertising could
also be achieved thus resulting in a disruptive growth to the advertising firms.
Hardware Analysis of Resonant Frequency Converter Using Isolated Circuits And...IJERD Editor
-LLC resonant frequency converter is basically a combo of series as well as parallel resonant ckt. For
LCC resonant converter it is associated with a disadvantage that, though it has two resonant frequencies, the
lower resonant frequency is in ZCS region[5]. For this application, we are not able to design the converter
working at this resonant frequency. LLC resonant converter existed for a very long time but because of
unknown characteristic of this converter it was used as a series resonant converter with basically a passive
(resistive) load. . Here, it was designed to operate in switching frequency higher than resonant frequency of the
series resonant tank of Lr and Cr converter acts very similar to Series Resonant Converter. The benefit of LLC
resonant converter is narrow switching frequency range with light load[6] . Basically, the control ckt plays a
very imp. role and hence 555 Timer used here provides a perfect square wave as the control ckt provides no
slew rate which makes the square wave really strong and impenetrable. The dead band circuit provides the
exclusive dead band in micro seconds so as to avoid the simultaneous firing of two pairs of IGBT’s where one
pair switches off and the other on for a slightest period of time. Hence, the isolator ckt here is associated with
each and every ckt used because it acts as a driver and an isolation to each of the IGBT is provided with one
exclusive transformer supply[3]. The IGBT’s are fired using the appropriate signal using the previous boards
and hence at last a high frequency rectifier ckt with a filtering capacitor is used to get an exact dc
waveform .The basic goal of this particular analysis is to observe the wave forms and characteristics of
converters with differently positioned passive elements in the form of tank circuits.
Simulated Analysis of Resonant Frequency Converter Using Different Tank Circu...IJERD Editor
LLC resonant frequency converter is basically a combo of series as well as parallel resonant ckt. For
LCC resonant converter it is associated with a disadvantage that, though it has two resonant frequencies, the
lower resonant frequency is in ZCS region [5]. For this application, we are not able to design the converter
working at this resonant frequency. LLC resonant converter existed for a very long time but because of
unknown characteristic of this converter it was used as a series resonant converter with basically a passive
(resistive) load. . Here, it was designed to operate in switching frequency higher than resonant frequency of the
series resonant tank of Lr and Cr converter acts very similar to Series Resonant Converter. The benefit of LLC
resonant converter is narrow switching frequency range with light load[6] . Basically, the control ckt plays a
very imp. role and hence 555 Timer used here provides a perfect square wave as the control ckt provides no
slew rate which makes the square wave really strong and impenetrable. The dead band circuit provides the
exclusive dead band in micro seconds so as to avoid the simultaneous firing of two pairs of IGBT’s where one
pair switches off and the other on for a slightest period of time. Hence, the isolator ckt here is associated with
each and every ckt used because it acts as a driver and an isolation to each of the IGBT is provided with one
exclusive transformer supply[3]. The IGBT’s are fired using the appropriate signal using the previous boards
and hence at last a high frequency rectifier ckt with a filtering capacitor is used to get an exact dc
waveform .The basic goal of this particular analysis is to observe the wave forms and characteristics of
converters with differently positioned passive elements in the form of tank circuits. The supported simulation
is done through PSIM 6.0 software tool
Amateurs Radio operator, also known as HAM communicates with other HAMs through Radio
waves. Wireless communication in which Moon is used as natural satellite is called Moon-bounce or EME
(Earth -Moon-Earth) technique. Long distance communication (DXing) using Very High Frequency (VHF)
operated amateur HAM radio was difficult. Even with the modest setup having good transceiver, power
amplifier and high gain antenna with high directivity, VHF DXing is possible. Generally 2X11 YAGI antenna
along with rotor to set horizontal and vertical angle is used. Moon tracking software gives exact location,
visibility of Moon at both the stations and other vital data to acquire real time position of moon.
“MS-Extractor: An Innovative Approach to Extract Microsatellites on „Y‟ Chrom...IJERD Editor
Simple Sequence Repeats (SSR), also known as Microsatellites, have been extensively used as
molecular markers due to their abundance and high degree of polymorphism. The nucleotide sequences of
polymorphic forms of the same gene should be 99.9% identical. So, Microsatellites extraction from the Gene is
crucial. However, Microsatellites repeat count is compared, if they differ largely, he has some disorder. The Y
chromosome likely contains 50 to 60 genes that provide instructions for making proteins. Because only males
have the Y chromosome, the genes on this chromosome tend to be involved in male sex determination and
development. Several Microsatellite Extractors exist and they fail to extract microsatellites on large data sets of
giga bytes and tera bytes in size. The proposed tool “MS-Extractor: An Innovative Approach to extract
Microsatellites on „Y‟ Chromosome” can extract both Perfect as well as Imperfect Microsatellites from large
data sets of human genome „Y‟. The proposed system uses string matching with sliding window approach to
locate Microsatellites and extracts them.
Importance of Measurements in Smart GridIJERD Editor
- The need to get reliable supply, independence from fossil fuels, and capability to provide clean
energy at a fixed and lower cost, the existing power grid structure is transforming into Smart Grid. The
development of a smart energy distribution grid is a current goal of many nations. A Smart Grid should have
new capabilities such as self-healing, high reliability, energy management, and real-time pricing. This new era
of smart future grid will lead to major changes in existing technologies at generation, transmission and
distribution levels. The incorporation of renewable energy resources and distribution generators in the existing
grid will increase the complexity, optimization problems and instability of the system. This will lead to a
paradigm shift in the instrumentation and control requirements for Smart Grids for high quality, stable and
reliable electricity supply of power. The monitoring of the grid system state and stability relies on the
availability of reliable measurement of data. In this paper the measurement areas that highlight new
measurement challenges, development of the Smart Meters and the critical parameters of electric energy to be
monitored for improving the reliability of power systems has been discussed.
Study of Macro level Properties of SCC using GGBS and Lime stone powderIJERD Editor
The document summarizes a study on the use of ground granulated blast furnace slag (GGBS) and limestone powder to replace cement in self-compacting concrete (SCC). Tests were conducted on SCC mixes with 0-50% replacement of cement with GGBS and 0-20% replacement with limestone powder. The results showed that replacing 30% of cement with GGBS and 15% with limestone powder produced SCC with the highest compressive strength of 46MPa, meeting fresh property requirements. The study concluded that this ternary blend of cement, GGBS and limestone powder can improve SCC properties while reducing costs.
Embedded machine learning-based road conditions and driving behavior monitoringIJECEIAES
Car accident rates have increased in recent years, resulting in losses in human lives, properties, and other financial costs. An embedded machine learning-based system is developed to address this critical issue. The system can monitor road conditions, detect driving patterns, and identify aggressive driving behaviors. The system is based on neural networks trained on a comprehensive dataset of driving events, driving styles, and road conditions. The system effectively detects potential risks and helps mitigate the frequency and impact of accidents. The primary goal is to ensure the safety of drivers and vehicles. Collecting data involved gathering information on three key road events: normal street and normal drive, speed bumps, circular yellow speed bumps, and three aggressive driving actions: sudden start, sudden stop, and sudden entry. The gathered data is processed and analyzed using a machine learning system designed for limited power and memory devices. The developed system resulted in 91.9% accuracy, 93.6% precision, and 92% recall. The achieved inference time on an Arduino Nano 33 BLE Sense with a 32-bit CPU running at 64 MHz is 34 ms and requires 2.6 kB peak RAM and 139.9 kB program flash memory, making it suitable for resource-constrained embedded systems.
Batteries -Introduction – Types of Batteries – discharging and charging of battery - characteristics of battery –battery rating- various tests on battery- – Primary battery: silver button cell- Secondary battery :Ni-Cd battery-modern battery: lithium ion battery-maintenance of batteries-choices of batteries for electric vehicle applications.
Fuel Cells: Introduction- importance and classification of fuel cells - description, principle, components, applications of fuel cells: H2-O2 fuel cell, alkaline fuel cell, molten carbonate fuel cell and direct methanol fuel cells.
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.
Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...University of Maribor
Slides from talk presenting:
Aleš Zamuda: Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapter and Networking.
Presentation at IcETRAN 2024 session:
"Inter-Society Networking Panel GRSS/MTT-S/CIS
Panel Session: Promoting Connection and Cooperation"
IEEE Slovenia GRSS
IEEE Serbia and Montenegro MTT-S
IEEE Slovenia CIS
11TH INTERNATIONAL CONFERENCE ON ELECTRICAL, ELECTRONIC AND COMPUTING ENGINEERING
3-6 June 2024, Niš, Serbia
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.
ACEP Magazine edition 4th launched on 05.06.2024Rahul
This document provides information about the third edition of the magazine "Sthapatya" published by the Association of Civil Engineers (Practicing) Aurangabad. It includes messages from current and past presidents of ACEP, memories and photos from past ACEP events, information on life time achievement awards given by ACEP, and a technical article on concrete maintenance, repairs and strengthening. The document highlights activities of ACEP and provides a technical educational article for members.
Empirical Analysis of Invariance of Transform Coefficients under Rotation
1. International Journal of Engineering Research and Development
e-ISSN: 2278-067X, p-ISSN: 2278-800X, www.ijerd.com
Volume 11, Issue 05 (May 2015), PP.43-51
43
Empirical Analysis of Invariance of Transform Coefficients under
Rotation
Sukhjeet Kaur Ranade1
, Sukhpreet Kaur2
1
Assistant Professor Department of Computer Science, Punjabi University, Patiala-147001
2
Department of Computer Science, Punjabi University, Patiala-147001
Abstract:- Rotationally invariant transforms, namely, angular radial transform and polar harmonic transforms
such as polar cosine transform, polar sine transform and polar complex exponential transforms, are used to
characterize image features for a number of applications like logo recognition, face recognition etc. But the
computation of features using these transforms is an expensive process due to their sinusoidal basis functions
which are quite computationally expensive. In this paper, the transform coefficients are analyzed to observe the
effect of rotation on each coefficient. The experimentation is done to find most robust transform coefficients
under rotation for each transform. Further, analysis is done to trace the effect of observed robust transform
coefficients in face recognition application. The results show that the recognition rate remains same for cases
when all transform coefficients are used for extracting image features and when only 50% to 60% observed
robust moments are used whereas the execution time decreases resulting in fast execution of application.
Keywords:- Angular radial transform, polar harmonic transforms, polar cosine transform, polar sine transform,
polar complex exponential transform, face recognition, feature extraction, Euclidean distance.
I. INTRODUCTION
Transform theory plays a fundamental role in image processing, as working with the transform of an
image instead of the image itself gives more insight into the properties of the image. Image transform is an
operation to change the default representation space of a digital image (spatial domain to another domain) so
that all the information present in the image is preserved in the transformed domain, but represented differently
and the transform is reversible, i.e., can be reverted to the spatial domain. Transforms are called shape
descriptors. These capture the significant properties of a function. These are the descriptors that correspond to
the projection of the function on a specific basis function. A transform is composed of two parts, i.e., radial and
angular part. The radial part of the basis function of a transform is sinusoidal function. Rotationally invariant
transforms are used for feature extraction in application related to pattern recognition. These applications are
based on properties like rotation invariance, scale invariance, orthogonality etc.
Rotation invariant transforms have the feature to be able to recognize a wide variety of objects
irrespective of their rotations. It is done by devising a set of features which are invariant to the image
orientation. The magnitude of the coefficients of rotation invariant transforms is rotation invariant. Transforms
are rotationally invariant when computed from ideal analog images. Mapping from analog images to digital
images causes magnitude invariance of transforms severely compromised due to the discretization errors in
computation. This affect the invariance property of transforms making some moments more sensitive and some
more robust to rotation. Invariance of transform coefficients is crucial in most of these applications, for e.g. the
performance of the pattern recognition critically depends on invariance of employed features with respect to
scaling and rotation.
The angular radial transform (ART) [1] and polar harmonic transforms (PHTs) [2] are region based
shape descriptors. These transforms are invariant under rotation transformation and can be made scale and
translation invariant after applying some geometric transformations. Above mentioned transforms possess low
computational complexity and high numerical stability; due to which they are used in many applications related
to image processing and pattern recognition like shape retrieval [1], logo recognition system [3], face detection
[5], image watermarking [6], and video security systems [4] [7], fingerprint classification [8]. Although these
transforms have low computational complexity but still they are expensive for real time applications due to their
sinusoidal basis function. The wide use of these transforms in various mentioned applications motivated us to
perform an analysis of transform coefficients under rotation using parameters given in [9] to find robust
transform coefficients, i.e. the moments having coefficients that are invariant or least invariant under the impact
of rotation. These robust transform coefficients can be only used for feature extraction instead of using all
coefficients up to some predefined order, thus reducing the computational complexity and making these
2. Empirical Analysis of Invariance of Transform Coefficients under Rotation
44
transforms more efficient for real time applications. Further, an analysis is performed using face recognition
application to illustrate that if only some percentage of observed robust transform coefficients are used for
above mentioned applications instead of all transform coefficients then whether the same recognition rate or
performance level can be achieved resulting in reduced computational complexity. The results are presented
based on recognition rate and execution time required for all cases.
The rest of the paper is organized as follows. An overview of considered rotationally invariant
transforms is given in Section II. Section III presents computational framework used for transforms. Empirical
analysis performed is divided into two parts, first part presents analysis performed on transform coefficients to
find robust moments and in second part the affect of observed robust moments is traced in face recognition
application. This is presented in Section IV. Section V presents conclusion.
II. ROTATIONALLY INVARIANT TRANSFORMS
Rotationally invariant transforms are defined on square image functions which do not change its value
under rotation. For a given image function, 𝑓 𝑥, 𝑦 , of size 𝑁 × 𝑁 pixels in a two-dimensional Cartesian
coordinate system, its rotation invariant transform coefficient, 𝐹𝑛𝑚 , of order n and repetition m is defined over a
unit disk in the continuous polar domain as follows :
𝐹𝑛𝑚 = λ 𝑓 𝑟, 𝜃 𝑉𝑛𝑚
∗
1
0
2𝜋
0
𝑟, 𝜃 𝑟 𝑑𝑟 𝑑𝜃 (1)
such that 𝑟 = 𝑥2 + 𝑦2 , 𝜃 = arctan(
𝑦
𝑥), λ is the normalization constant and 𝑉𝑛𝑚
∗
𝑟, 𝜃 is the complex
conjugate of the basis function, 𝑉𝑛𝑚 𝑟, 𝜃 , which is separable along the radial and angular directions, i.e.,
𝑉𝑛𝑚 𝑟, 𝜃 = 𝑅 𝑛𝑚 𝑟 𝐴 𝑚 𝜃 (2)
Each transform is uniquely defined by its radial basis function, 𝑅 𝑛𝑚 (𝑟), and in order to provide rotational
invariance, the angular basis function, Am(θ), is given by:
𝐴 𝑚 𝜃 = 𝑒 𝑗𝑚𝜃
; 𝑗 = −1 (3)
A. Angular Radial Transform (ART)
The ARTs coefficient, 𝐴 𝑛𝑚 , of a continuous function, 𝑓 𝑟, 𝜃 , of order n and repetition m in polar
domain are extracted over a unit disk using the following formula:
𝐴 𝑛𝑚 =
1
2𝜋
𝑓 𝑟, 𝜃 𝑉𝑛𝑚
∗
𝑟, 𝜃 𝑟 𝑑𝑟 𝑑𝜃
1
0
2𝜋
0
(4)
where 𝑛 ≥ 0 and 𝑚 ≥ 0.
The radial function of ARTs is defined as:
𝑅 𝑛
𝐴𝑅𝑇
𝑟 =
1, 𝑛 = 0
2 cos 𝜋𝑛𝑟 , 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒
(5)
ART is used for invariant shape retrieval [1], logo recognition system [3], face detection [5], image
watermarking [6], video security system [4] [7] and cephaloetric X-ray registration [10].
B. Polar Harmonic Transforms (PHTs)
Yap et. al [2] introduced a set of transforms called polar harmonic transforms (PHTs), which can be
used to generate rotation invariant features. PHTs consist of three different transforms, namely, polar complex
exponential transform (PCET), polar cosine transform (PCT) and polar sine transform (PST).
Polar complex exponential transform (PCET)
The PCETs coefficient of order |n|≥0 and repetition |m|≥0 is given in polar domain by:
3. Empirical Analysis of Invariance of Transform Coefficients under Rotation
45
𝐹𝑛𝑚
𝑃𝐶𝐸𝑇
=
1
𝜋
𝑓 𝑟, 𝜃 [𝑉𝑛𝑚
𝑃𝐶𝐸𝑇
𝑟, 𝜃 ]∗
𝑟 𝑑𝑟 𝑑𝜃 (6)
1
0
2𝜋
0
where 𝑉𝑛𝑚
𝑃𝐶𝐸𝑇
𝑟, 𝜃 is PCET basis function having radial basis function, 𝑅 𝑛
𝑃𝐶𝐸𝑇
𝑟 :
𝑅 𝑛
𝑃𝐶𝐸𝑇
𝑟 = 𝑒 𝑗2𝜋𝑟2
(7)
The other two sets of harmonic transforms, PCTs and PSTs, are defined as:
Polar cosine transform (PCT)
PCTs coefficients are defined as:
𝐹𝑛𝑚
𝑃𝐶𝑇
= 𝜆 𝑓 𝑟, 𝜃 [𝑉𝑛𝑚
𝑃𝐶𝑇
𝑟, 𝜃 ]∗
𝑟 𝑑𝑟 𝑑𝜃 (8)
1
0
2𝜋
0
where 𝑛 ≥ 0, 𝑚 ≥ 0 and
𝑉𝑛𝑚
𝑃𝐶𝑇
𝑟, 𝜃 = 𝑅 𝑛
𝑃𝐶𝑇
𝑟 𝑒 𝑗𝑚𝜃
= cos 𝜋𝑛𝑟2
𝑒 𝑗𝑚𝜃
(9)
where
𝜆 =
1
𝜋
𝑛 = 0
2
𝜋
𝑛 ≠ 0
(10)
Polar sine transform (PST)
PSTs coefficients are defined as:
𝐹𝑛𝑚
𝑃𝑆𝑇
= 𝜆 𝑓 𝑟, 𝜃 [𝑉𝑛𝑚
𝑃𝑆𝑇
𝑟, 𝜃 ]∗
𝑟 𝑑𝑟 𝑑𝜃 (11)
1
0
2𝜋
0
where 𝑛 ≥ 1, 𝑚 ≥ 0 and
𝑉𝑛𝑚
𝑃𝑆𝑇
𝑟, 𝜃 = 𝑅 𝑛
𝑃𝑆𝑇
𝑟 𝑒 𝑗𝑚𝜃
= sin 𝜋𝑛𝑟2
𝑒 𝑗𝑚𝜃
(12)
where
𝜆 = 2
𝜋 (13)
PHTs are used in applications like fingerprint classification [8].
III. COMPUTATIONAL FRAMEWORK FOR TRANSFORMS
In digital image processing, the image function, 𝑓 𝑥, 𝑦 , is discrete, whereas transform invariants are
defined over the unit disk in continuous polar domain. However, the discrete image function can be converted
into polar domain using a suitable interpolation process [11] but this mapping introduces interpolation error
which affects the accuracy in computation [12]. To avoid interpolation error, the traditional method is used to
compute transform coefficients in the Cartesian domain directly using zeroth-order approximation (ZOA) of the
double integration involved in Eq. (1) as follows:
𝐹𝑛𝑚 = 𝜆 𝑓 𝑖, 𝑘 𝑅 𝑛𝑚
𝑁−1
𝑘=0
𝑁−1
𝑖=0
𝑟𝑖𝑘 𝑒−𝑗𝑚 𝜃 𝑖𝑘 ∆𝑥 ∆𝑦 (14)
such that λ is the normalization constant depending on the transform used and
∆𝑥 = ∆𝑦 =
2
𝐷
, 𝑟𝑖𝑘
2
= 𝑥𝑖
2
+ 𝑦 𝑘
2
≤ 1 and 𝜃𝑖𝑘 = arctan(
𝑦 𝑘
𝑥𝑖
) (15)
4. Empirical Analysis of Invariance of Transform Coefficients under Rotation
46
and the coordinates (𝑥𝑖, 𝑦 𝑘 ) are given by
𝑥𝑖 =
2𝑖−𝑁+1
𝐷
, 𝑦 𝑘 =
2𝑘−𝑁+1
𝐷
, 𝑖, 𝑘 = 0,1, … 𝑁 − 1 16
where
𝐷 =
𝑁 𝑓𝑜𝑟 𝑖𝑛𝑛𝑒𝑟 𝑑𝑖𝑠𝑘
𝑁 2 𝑓𝑜𝑟 𝑜𝑢𝑡𝑒𝑟 𝑑𝑖𝑠𝑘
(17)
The coordinate (𝑥𝑖, 𝑦 𝑘 ) is the centre of the square pixel grid (𝑖, 𝑘). This mapping converts the square
domain into an approximated unit disk. Many transform-based applications use inner disk for computing the
coefficients therefore we have taken 𝐷 = 𝑁 and ∆𝑥 = ∆𝑦 =
2
𝑁
.
IV. EMPIRICAL ANALYSIS RESULTS
A. Empirical analysis done to find most robust moments
The algorithms for the computation of transforms are implemented in Microsoft Visual Studio 2010
under Microsoft Window 7 environment on Intel 2.26 GHz processor with 3 GB RAM. The experimentation is
performed with twelve standard 256-level gray scale images of size 128 × 128 pixels given in Table 1.
The rotation invariance property of the transforms is analysed for maximum order, 𝑛 𝑚𝑎𝑥 = 10 and
maximum repetition 𝑚 𝑚𝑎𝑥 = 10. Let 𝐹𝑛𝑚
𝑡
represent transform coefficient at order n and repetition m for a
particular transform t. The parameter 𝐶𝑛𝑚 (𝜃) at 𝜃 = 0°
, 5°
, … . , 45°
is computed for each transform using the
formula [9]:
𝐶𝑛𝑚 𝜃 = 𝐹𝑛𝑚 (𝜃) 𝐹𝑛𝑚 (0°
) (18)
Further, the deviation is measured by computing the parameter:
𝜎2
=
1
10
𝐶𝑛𝑚 (𝜃𝑖) − 1 2
(19)10
𝑖=1
where 𝜃𝑖 = 0°
, 5°
, … . , 45°
.
The transform coefficients for which the value of parameter 𝜎2
is least are considered more robust
compared to moments that have high value. The results were obtained by considering the average deviation of
all the 12 images given in Table 1. It was observed that some transform coefficients at particular order and
repetition show high deviation for a particular image which were excluded during calculation of average
deviation. These high deviating order and repetition indicated that the obtained most robust transform
coefficients are image dependent and the results also show that PST has least deviating nature among all other
transforms considered followed by ART. Figure 1 show the graph plotted for minimum and maximum moments
and their corresponding average 𝐶𝑛𝑚 𝜃 values for each transform under investigation.
As the results obtained from this analysis were observed to be image dependent so to further trace the
effect of robust transform coefficients using face recognition application the same analysis is conducted on the
training image set used in face recognition application. This is done for only least deviating transforms (i.e.
polar sine transform and angular radial transform) among transforms under investigation that is concluded after
the analysis done on the 12 images given in Table 1.
Table 1. Twelve standard gray scale images used for experimentation
Barbara Bridge Cameraman Clock
5. Empirical Analysis of Invariance of Transform Coefficients under Rotation
47
Fishing Boat Gold Hill House Jet Plane
Mandrill Peppers Pirate Tree
A. Analysis to trace applicability of results of sub-section A
The results obtained after analysis of transform coefficients using training image set were applied to
face recognition application. The face recognition application employed is used to recognize the most relevant
face from the database when query face image is presented to the application. The Euclidean distance (ED) is
used as a similarity measure between the query image features and the features extracted from the images in the
database. Euclidean distance is defined as:
𝐸𝐷 𝐹 𝐷
, 𝐹 𝑄
= (𝐹𝑖
𝑄
− 𝐹𝑖
𝐷
)2𝑛
𝑖=1 (20)
where, 𝐹 𝐷
is the images in database and 𝐹 𝑄
is the query image presented to the application, 𝐹 𝐷
= 𝐹1
𝐷,
𝐹2
𝐷
, . . . , 𝐹𝑛
𝐷
are features extracted from the images in database, 𝐹 𝑄
= 𝐹1
𝑄,
𝐹2
𝑄
, . . . , 𝐹𝑛
𝑄
are features extracted from the query
image and n is the number of these features. The database image having the least Euclidean distance with the
presented query image is considered the best match for the query image. To trace the applicability of above
analysis results to face recognition application the AT&T “The Database of Faces” (formerly “The Olivetti
Research Lab (ORL) Database of Faces”) is used. The AT&T contains 400 face images of 40 different persons
with 10 images of each person in a different folder.
6. Empirical Analysis of Invariance of Transform Coefficients under Rotation
48
Fig. 1. Avg.𝑪 𝒏𝒎 𝜽 values vs. angle of rotation for least and most deviating transform coefficients
For this analysis we have taken 100 face images (first 5 of first 20 subjects) in the training set which
acts as database and all train and test images are resized to canvas size 128 × 128 . The test database consists of
1000 images which were developed using other 5 images of same 20 subjects by rotating (inner disk rotation)
them at multiple angles from 𝜃 = 0°
, 5°
, … . , 90°
. Some used train and test images are given in Table 2.
Table 2. Examples of train and test images used for face recognition analysis
Train Images Test Images
0.9
0.95
1
1.05
1.1
1.15
1.2
1.25
1.3
1.35
0 10 20 30 40 50
AverageCnm(θ)
Angle of Rotation, θ
ART Min (1,0)
ART Max (8,4)
PCT Min (0,1)
PCT Max (9,0)
PST Min (1,0)
PST Min (3,0)
PST Max (6,0)
PCET Min (0,1)
PCET Max (10,-6)
7. Empirical Analysis of Invariance of Transform Coefficients under Rotation
49
In this analysis the recognition rate of faces is considered against execution time needed. The
comparison is done by considering all and reduced number of transform coefficients for feature extraction. The
observed robust transform coefficients obtained from analysis of train images are considered in ascending order
of their deviation. Then from these ascending transform coefficients the face recognition analysis is performed
by taking 10% transform coefficients to 100% transform coefficients for feature extraction. The results are
presented based on recognition rate and execution time needed. The performance of the face recognition
application is based on how well the query faces can be matched with correct faces in database in presence of
rotation at various angles. In this experimentation PST and ART are used for feature extraction at maximum
order, 𝑛 𝑚𝑎𝑥 = 10 and maximum repetition 𝑚 𝑚𝑎𝑥 = 10, making a total of 110 transform coefficients for PST
and 121 for ART (taking 𝑛 ≥ 0 and 𝑚 ≥ 0).
After experimentation, it was observed that the rate of recognition becomes stable when 50% - 60%
transform coefficients are used for feature extraction. This means instead of using all transform coefficients for
feature extraction only 50% - 60% robust transform coefficients can be utilized, thus decreasing the time
complexity.
Table 3. Percentage of robust transform coefficients used for feature extraction against recognition rate
obtained and execution time needed for PST
Percentage of moments
used
No. of Moments Recognition Rate Time taken
(in sec)
10% 11 84.8% 25.396
20% 22 88.3% 51.152
30% 33 90.6% 76.518
40% 44 92% 129.167
50% 55 93% 130.511
60% 66 92.6% 166.664
70% 77 93% 179.416
80% 88 93% 207.153
90% 99 93% 231.77
100% 110 93% 255.498
Table 3 and Table 4 represent the percentage of robust transform coefficients used for feature
extraction against recognition rate obtained and execution time needed for PST and ART respectively. Figure 2
and Figure 3 shows the graph plotted against percentage of transform coefficients used and recognition rate for
PST and ART respectively. The results show that the execution time reduces by about half when only 50%
transform coefficients are used.
8. Empirical Analysis of Invariance of Transform Coefficients under Rotation
50
Table 4. Percentage of robust transform coefficients used for feature extraction against recognition rate obtained
and execution time needed for ART
Percentage of moments
used
No. of Moments Recognition Rate Time taken
(in sec)
10% 12 79.3% 30.607
20% 24 91% 60.107
30% 36 91.9% 87.766
40% 48 90% 115.846
50% 60 92% 128.263
60% 72 93% 160.587
70% 84 92.4% 186.67
80% 96 93% 218.534
90% 108 92.2% 244.667
100 121 93% 298.444
Fig. 2. Recognition rate vs. percentage of transform coefficients used for feature extraction using PST
Fig. 3. Recognition rate vs. percentage of transform coefficients used for feature extraction using ART
50
60
70
80
90
100
0 10 20 30 40 50 60 70 80 90 100
RecognitionRate(%)
Percentage of transform coefficients used (%)
50
60
70
80
90
100
0 10 20 30 40 50 60 70 80 90 100
RecognitionRate(%)
Percentage of transform coefficients used (%)
9. Empirical Analysis of Invariance of Transform Coefficients under Rotation
51
V. CONCLUSION
Rotationally invariant transforms, namely, angular radial transform and polar harmonic transforms such
as polar cosine transform, polar sine transform and polar complex exponential transforms, are used for feature
extraction in various image processing applications like logo recognition, face recognition etc. However,
mapping from analog images to digital images causes magnitude invariance of transforms severely
compromised due to the discretization errors in computation. This affect the invariance property of transforms
making some moments more sensitive and some more robust to rotation. Invariance of transform coefficients is
crucial in most of these applications. These features are analyzed in this paper and the effect of obtained results
is traced using face recognition application and concluded as:
Among all transforms under investigation PSTs have the least deviating nature in case of rotation
invariance followed by ART.
It was also observed that the robust moments are image dependent showing high deviating nature at some
particular orders and repetitions for particular images.
The effect of robust transform coefficients traced in face recognition application illustrates that reduced
number of coefficients (robust) between 50% to 60% can be used instead of using all coefficients to
achieve same recognition rate but at low computational complexity.
REFERENCES
[1]. Bober M., MPEG-7 Visual shape descriptors. IEEE Trans. on Circuits and Systems for Video ., 11 (6)
(2001) 716-719.
[2]. Yap P.T., Jiang X., Kot A.C., Two-dimensional polar harmonic transforms for invariant image
representation. IEEE Trans. on Pattern Analysis and Machine Intelligence. 32 (7) (2010) 1259-1270.
[3]. Wahdan O.M., Omar K. and Nasrudin M.F., Logo recognition system using angular radial transform
descriptors. Journal of Computer Science. 7 (9) (2011) 1416-1422.
[4]. He D., Sun Q. and Tian Q., A semi-fragile object based video authentication system. ISCAS (2003).
[5]. Fang J. and Qiu G., Human face detection using angular radial transform and support vector machines.
[6]. Singh C. and Ranade S.K., Geometrically invariant and high capacity image watermarking scheme
using accurate radial transform. Optics and Laser Technology. 54 (2013) 176-184.
[7]. Lee S.H., Sharma S., Sang L., Park J.-I. and Park Y.G., An intelligent video security system using
object tracking and shape recognition. ACVIS LNCS Springer-Verlag Berlin Heidelberg. 6915 (2011)
471-482.
[8]. Liu M., Jiangz X., Chichung A. K. and Yap P.-T., Application of polar harmonic transforms to
fingerprint classification. World Scientific Publishing. (2011).
[9]. [Singh C., Sharma P. and Upneja R., On image reconstruction, numerical stability, and invariance of
orthogonal radial moments and radial harmonic transforms. Pattern Recognition and Image Analysis.
21 (4) (2011) 663-676.
[10]. Singh C. and Kaur A., Cephalometric X-Ray Registration using Angular Radial Transform.
International Conference on Recent Advances and Future Trends in Information Technology. (2012)
18-22.
[11]. Xin Y., Pawlak M. and Liao S., Accurate calculation of moments in polar co-ordinates. IEEE Trans. on
image processing. 16 (2007) 581-587.
[12]. Singh C. and Walia E., Computation of Zernike moments in improved polar configuration. IET J.
Image Processing. 3 (2009) 217-227.
[13]. Rodtook S. and Makhanov S. S., Numerical experiments on the accuracy of rotation moments
invariants. Image and Vision Computing. 23 (2005) 577-586.
[14]. Omaia D., Poel J. D. V. and Batista L. V., 2D-DCT distance based face recognition using a reduced
number of coefficients.
[15]. Singh C. and Aggarwal A., A noise resistant image matching method using angular radial transform.
Digital Signal Processing. 33 (2014) 116-124.