Proposed approach explores a new framework for curved video text detection and extraction. The algorithm first utilizes a Gaussian filter based Color Edge Enhancement followed by a Gray level Co-occurrence matrix feature extraction method for text detection. Secondly, a Connected Component filtering method is utilized to generate clear localization result and at last, a Round Scan method is performed to extract curved text and generate binary result for recognition by OCR. Experiments on various curved video data and Hua’s horizontal video text dataset shows the effectiveness and robustness of the proposed method.
Automated Colorization of Grayscale Images Using Texture DescriptorsIDES Editor
A novel example-based process for automated
colorization of grayscale images using texture descriptors
(ACTD) without any human intervention is proposed. By
analyzing a set of sample color images, coherent regions of
homogeneous textures are extracted. A multi-channel filtering
technique is used for texture-based image segmentation. For
each area of interest, state of the art texture descriptors are
then computed and stored, along with corresponding color
information. These texture descriptors and the color
information are used for colorization of a grayscale image with
similar textures. Given a grayscale image to be colorized, the
segmentation and feature extraction processes are repeated.
The texture descriptors are used to perform Content-Based
Image Retrieval (CBIR). The colorization process is performed
by chroma replacement. This research finds numerous
applications, ranging from classic film restoration and
enhancement, to adding valuable information into medical and
satellite imaging, and to enhance the detection of objects from
x-ray images at the airports.
MMFO: modified moth flame optimization algorithm for region based RGB color i...IJECEIAES
Region-based color image segmentation is elementary steps in image processing and computer vision. The region-based color image segmentation has faced the problem of multidimensionality. The color image is considered in five-dimensional problems, in which three dimensions in color (RGB) and two dimensions in geometry (luminosity layer and chromaticity layer). In this paper, L*a*b color space conversion has been used to reduce the one dimension and geometrically it converts in the array hence the further one dimension has been reduced. This paper introduced, an improved algorithm modified moth flame optimization (MMFO) algorithm for RGB color image segmentation which is based on bio-inspired techniques. The simulation results of MMFO for region based color image segmentation are performed better as compared to PSO and GA, in terms of computation times for all the images. The experiment results of this method gives clear segments based on the different color and the different number of clusters is used during the segmentation process.
An Efficient Filtering Technique for Denoising Colour Images IJECEIAES
Single-sensor digital cameras capture image with the aid of masking the sensor surface along a colour filter array(CFA) such that every sensor pixel solely samples certain of three primary colour values i.e., R (red), G (green) and B (blue). To get a full-colour image, an interpolation method commonly referred in conformity with CFA demosaicking is required to estimate the other two contributions for producing a full-colour image. But, the clutter in imaging sensors not only corrupts the colour filter array but also introduces artifacts at some stage in the colour interpolation step and affects the characteristics of image. To acquire high quality full-colour image, a kind of viable and effective interpolation algorithm based over gradient is used. This technique can remove the noise effectively by retaining image border and detail data clearly.
Face Recognition Using Neural Network Based Fourier Gabor Filters & Random Pr...CSCJournals
Face detection and recognition has many applications in a variety of fields such as authentication, security, video surveillance and human interaction systems. In this paper, we present a neural network system for face recognition. Feature vector based on Fourier Gabor filters is used as input of our classifier, which is a Back Propagation Neural Network (BPNN). The input vector of the network will have large dimension, to reduce its feature subspace we investigate the use of the Random Projection as method of dimensionality reduction. Theory and experiment indicates the robustness of our solution.
Research Inventy : International Journal of Engineering and Scienceresearchinventy
Research Inventy : International Journal of Engineering and Science is published by the group of young academic and industrial researchers with 12 Issues per year. It is an online as well as print version open access journal that provides rapid publication (monthly) of articles in all areas of the subject such as: civil, mechanical, chemical, electronic and computer engineering as well as production and information technology. The Journal welcomes the submission of manuscripts that meet the general criteria of significance and scientific excellence. Papers will be published by rapid process within 20 days after acceptance and peer review process takes only 7 days. All articles published in Research Inventy will be peer-reviewed.
Review of ocr techniques used in automatic mail sorting of postal envelopessipij
This paper presents a review of various OCR techniq
ues used in the automatic mail sorting process. A
complete description on various existing methods fo
r address block extraction and digit recognition th
at
were used in the literature is discussed. The objec
tive of this study is to provide a complete overvie
w about
the methods and techniques used by many researchers
for automating the mail sorting process in postal
service in various countries. The significance of Z
ip code or Pincode recognition is discussed.
Automated Colorization of Grayscale Images Using Texture DescriptorsIDES Editor
A novel example-based process for automated
colorization of grayscale images using texture descriptors
(ACTD) without any human intervention is proposed. By
analyzing a set of sample color images, coherent regions of
homogeneous textures are extracted. A multi-channel filtering
technique is used for texture-based image segmentation. For
each area of interest, state of the art texture descriptors are
then computed and stored, along with corresponding color
information. These texture descriptors and the color
information are used for colorization of a grayscale image with
similar textures. Given a grayscale image to be colorized, the
segmentation and feature extraction processes are repeated.
The texture descriptors are used to perform Content-Based
Image Retrieval (CBIR). The colorization process is performed
by chroma replacement. This research finds numerous
applications, ranging from classic film restoration and
enhancement, to adding valuable information into medical and
satellite imaging, and to enhance the detection of objects from
x-ray images at the airports.
MMFO: modified moth flame optimization algorithm for region based RGB color i...IJECEIAES
Region-based color image segmentation is elementary steps in image processing and computer vision. The region-based color image segmentation has faced the problem of multidimensionality. The color image is considered in five-dimensional problems, in which three dimensions in color (RGB) and two dimensions in geometry (luminosity layer and chromaticity layer). In this paper, L*a*b color space conversion has been used to reduce the one dimension and geometrically it converts in the array hence the further one dimension has been reduced. This paper introduced, an improved algorithm modified moth flame optimization (MMFO) algorithm for RGB color image segmentation which is based on bio-inspired techniques. The simulation results of MMFO for region based color image segmentation are performed better as compared to PSO and GA, in terms of computation times for all the images. The experiment results of this method gives clear segments based on the different color and the different number of clusters is used during the segmentation process.
An Efficient Filtering Technique for Denoising Colour Images IJECEIAES
Single-sensor digital cameras capture image with the aid of masking the sensor surface along a colour filter array(CFA) such that every sensor pixel solely samples certain of three primary colour values i.e., R (red), G (green) and B (blue). To get a full-colour image, an interpolation method commonly referred in conformity with CFA demosaicking is required to estimate the other two contributions for producing a full-colour image. But, the clutter in imaging sensors not only corrupts the colour filter array but also introduces artifacts at some stage in the colour interpolation step and affects the characteristics of image. To acquire high quality full-colour image, a kind of viable and effective interpolation algorithm based over gradient is used. This technique can remove the noise effectively by retaining image border and detail data clearly.
Face Recognition Using Neural Network Based Fourier Gabor Filters & Random Pr...CSCJournals
Face detection and recognition has many applications in a variety of fields such as authentication, security, video surveillance and human interaction systems. In this paper, we present a neural network system for face recognition. Feature vector based on Fourier Gabor filters is used as input of our classifier, which is a Back Propagation Neural Network (BPNN). The input vector of the network will have large dimension, to reduce its feature subspace we investigate the use of the Random Projection as method of dimensionality reduction. Theory and experiment indicates the robustness of our solution.
Research Inventy : International Journal of Engineering and Scienceresearchinventy
Research Inventy : International Journal of Engineering and Science is published by the group of young academic and industrial researchers with 12 Issues per year. It is an online as well as print version open access journal that provides rapid publication (monthly) of articles in all areas of the subject such as: civil, mechanical, chemical, electronic and computer engineering as well as production and information technology. The Journal welcomes the submission of manuscripts that meet the general criteria of significance and scientific excellence. Papers will be published by rapid process within 20 days after acceptance and peer review process takes only 7 days. All articles published in Research Inventy will be peer-reviewed.
Review of ocr techniques used in automatic mail sorting of postal envelopessipij
This paper presents a review of various OCR techniq
ues used in the automatic mail sorting process. A
complete description on various existing methods fo
r address block extraction and digit recognition th
at
were used in the literature is discussed. The objec
tive of this study is to provide a complete overvie
w about
the methods and techniques used by many researchers
for automating the mail sorting process in postal
service in various countries. The significance of Z
ip code or Pincode recognition is discussed.
Wavelet-Based Color Histogram on Content-Based Image RetrievalTELKOMNIKA JOURNAL
The growth of image databases in many domains, including fashion, biometric, graphic design,
architecture, etc. has increased rapidly. Content Based Image Retrieval System (CBIR) is a technique used
for finding relevant images from those huge and unannotated image databases based on low-level features
of the query images. In this study, an attempt to employ 2nd level Wavelet Based Color Histogram (WBCH)
on a CBIR system is proposed. Image database used in this study are taken from Wang’s image database
containing 1000 color images. The experiment results show that 2nd level WBCH gives better precision
(0.777) than the other methods, including 1st level WBCH, Color Histogram, Color Co-occurrence Matrix,
and Wavelet texture feature. It can be concluded that the 2nd Level of WBCH can be applied to CBIR system.
Performance Evaluation of Image Edge Detection Techniques CSCJournals
The success of an image recognition procedure is related to the quality of the edges marked. The
aim of this research is to investigate and evaluate edge detection techniques when applied to
noisy images at different scales. Sobel, Prewitt, and Canny edge detection algorithms are
evaluated using artificially generated images and comparison criteria: edge quality (EQ) and map
quality (MQ). The results demonstrated that the use of these criteria can be utilized as an aid for
further analysis and arbitration to find the best edge detector for a given image.
Data Steganography for Optical Color Image CryptosystemsCSCJournals
In this paper, an optical color image cryptosystem with a data hiding scheme is proposed. In the proposed optical cryptosystem, a confidential color image is embedded into the host image of the same size. Then the stego-image is encrypted by using the double random phase encoding algorithm. The seeds to generate random phase data are hidden in the encrypted stego-image by a content-dependent and low distortion data embedding technique. The confidential image and secret data delivery is accomplished by hiding the image into the host image and embedding the data into the encrypted stego-image. Experimental results show that the proposed data steganographic cryptosystem provides large data hiding capacity and high reconstructed image quality.
Text-Image Separation in Document Images using Boundary/Perimeter DetectionIDES Editor
Document analysis plays an important role in office
automation, especially in intelligent signal processing. The
proposed system consists of two modules: block segmentation
and block identification. In this approach, first a document is
segmented into several non-overlapping blocks by utilizing a
novel recursive segmentation technique, and then extracts
the features embedded in each segmented block are extracted.
Two kinds of features, connected components and image
boundary/perimeter features are extracted. Document with
text inside image pose limitations in earlier reported literature.
This is taken care of by applying additional pass of the Run
Length Smearing on the extracted image that contains text.
Proposed scheme is independent of type and language of the
document.
Gabor filter is a powerful way to enhance biometric images like fingerprint images in order to extract correct features from these images, Gabor filter used in extracting features directly asin iris images, and sometimes Gabor filter has been used for texture analysis. In fingerprint images The even symmetric Gabor filter is contextual filter or multi-resolution filter will be used to enhance fingerprint imageby filling small gaps (low-pass effect) in the direction of the ridge (black regions) and to increase the discrimination between ridge and valley (black and white regions) in the direction, orthogonal to the ridge, the proposed method in applying Gabor filter on fingerprint images depending on translated fingerprint image into binary image after applying some simple enhancing methods to partially overcome time consuming problem of the Gabor filter.
Content Based Image Retrieval (CBIR) is one of the
most active in the current research field of multimedia retrieval.
It retrieves the images from the large databases based on images
feature like color, texture and shape. In this paper, Image
retrieval based on multi feature fusion is achieved by color and
texture features as well as the similarity measures are
investigated. The work of color feature extraction is obtained by
using Quadratic Distance and texture features by using Pyramid
Structure Wavelet Transforms and Gray level co-occurrence
matrix. We are comparing all these methods for best image
retrieval
Analysis of combined approaches of CBIR systems by clustering at varying prec...IJECEIAES
The image retrieving system is used to retrieve images from the image database. Two types of Image retrieval techniques are commonly used: content-based and text-based techniques. One of the well-known image retrieval techniques that extract the images in an unsupervised way, known as the cluster-based image retrieval technique. In this cluster-based image retrieval, all visual features of an image are combined to find a better retrieval rate and precisions. The objectives of the study were to develop a new model by combining the three traits i.e., color, shape, and texture of an image. The color-shape and colortexture models were compared to a threshold value with various precision levels. A union was formed of a newly developed model with a color-shape, and color-texture model to find the retrieval rate in terms of precisions of the image retrieval system. The results were experimented on on the COREL standard database and it was found that the union of three models gives better results than the image retrieval from the individual models. The newly developed model and the union of the given models also gives better results than the existing system named clusterbased retrieval of images by unsupervised learning (CLUE).
Query Image Searching With Integrated Textual and Visual Relevance Feedback f...IJERA Editor
There are many researchers who have studied the relevance feedback in the literature of content based image
retrieval (CBIR) community, but none of CBIR search engines support it because of scalability, effectiveness
and efficiency issues. In this, we had implemented an integrated relevance feedback for retrieving of web
images. Here, we had concentrated on integration of both textual features (TF) and visual features (VF) based
relevance feedback (RF), simultaneously we also tested them individually. The TFRF employs and effective
search result clustering (SRC) algorithm to get salient phrases. Then a new user interface (UI) is proposed to
support RF. Experimental results show that the proposed algorithm is scalable, effective and accurated
Efficient fingerprint image enhancement algorithm based on gabor filtereSAT Publishing House
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology
The development of multimedia system technology in Content based Image Retrieval (CBIR) System is
one in every of the outstanding area to retrieve the images from an oversized collection of database. The feature
vectors of the query image are compared with feature vectors of the database images to get matching images.It is
much observed that anyone algorithm isn't beneficial in extracting all differing kinds of natural images. Thus an
intensive analysis of certain color, texture and shape extraction techniques are allotted to spot an efficient CBIR
technique that suits for a selected sort of images. The Extraction of an image includes feature description and
feature extraction. During this paper, we tend to projected Color Layout Descriptor (CLD), grey Level Co-
Occurrences Matrix (GLCM), Marker-Controlled Watershed Segmentation feature extraction technique that
extract the matching image based on the similarity of Color, Texture and shape within the database. For
performance analysis, the image retrieval timing results of the projected technique is calculated and compared
with every of the individual feature.
Experimental Testing Of Partially Encased Composite Beam ColumnsIJERA Editor
The past few decades have seen outstanding advances in the use of composite materials in structural applications. There can be little doubt that, within engineering circles, composites have revolutionized traditional design concepts and made possible an unparalleled range of new and exciting possibilities as viable materials for construction. In addition to the well-known advantages of composite columns, partially encased composite columns offered simplified beam-to-column connection as well as reduced or omitted shuttering thus achieved more cost effective construction. Some companies have patented these new types of partially encased composite column made of light welded steel shapes; moreover, the Canadian Institute of Steel construction CISC has recognized and codified this type of columns. In This paper, Partially Encased Composite Beam Columns is introduced; experimental studies are made on five partially encased beam columns to investigate the behavior of eccentrically loaded partially encased composite columns using different parameters.
Optimization of Polyphenol Content in Green Tea and studying its Antioxidant ...IJERA Editor
The aim of my project is to optimize the level of Polyphenol content present in Green Tea at various
temperatures. During the project various combinations of temperatures and time intervals were used to obtain
the Green Tea extract and the polyphenol content of all these extracts were estimated. Both unfermented and
artificial fermentation condtions were used to obtain the extract. The extracts were further used to screen the
various contents of the extract both normally and after purifying the sample with PVP (Polyvinyl pyrrlidone).
The extract with the highest content of polyphenols were further used to estimate the antioxidant property after
purification with column chromatography.
Survey of Smartphone applications based on OBD-II for Intelligent Transportat...IJERA Editor
Highway transportation is supported with several technologies to decrease risk factors and to obtain secure drive.
With improved software and hardware smartphone technology is able to monitor the useful information from
information network and especially it helps to maintain and control better traffic management for ITS. In this
study accession systems to electronic control unit are examined and also access procedure to vehicle status via
onboard diagnostic (OBD) also demonstrated. Additionally vehicle and environment information evaluation and
prevention of accident risks with smartphone technology are also indicated.
Retention Behavior of Lead Ion in Soil Bentonite LinerIJERA Editor
In this study, it is proposed to obtain breakthrough curves for commonly occurring lead ions in any effluents
through locally available soil amended with 10% bentonite and determine the diffusion coefficients. The
theoretical breakthrough curves of migrating ions in the soil column experiment are generated using
mathematical equation considering effective diffusion coefficients , knowing soil parameters and hydraulic
head. These curves are then compared with experimental curves. In cases where the theoretical and experimental
breakthrough curve do not match, there would be need to consider other parameter retardation factor along with
diffusion coefficient. Theoretical curves are generated for sets of diffusion coefficient and retardation factor.
The sets which give theoretical curve close to experimentally determined breakthrough curves are accepted.
Thus it may be possible to bring out the condition for the dominance of diffusion coefficient and retardation
factor. Then knowing the values of diffusion coefficient and retardation factor along with soil porosity and
hydraulic gradient it is possible to predict the breakthrough times of different ions in the soil. In this work the
breakthrough times of lead ion for the soil of 1m and 0.5m are established. The studies can be extended for any
ion or soil after establishing diffusion coefficient and retardation for the considered ions in the selected liner
under different hydrological regimes.
Wavelet-Based Color Histogram on Content-Based Image RetrievalTELKOMNIKA JOURNAL
The growth of image databases in many domains, including fashion, biometric, graphic design,
architecture, etc. has increased rapidly. Content Based Image Retrieval System (CBIR) is a technique used
for finding relevant images from those huge and unannotated image databases based on low-level features
of the query images. In this study, an attempt to employ 2nd level Wavelet Based Color Histogram (WBCH)
on a CBIR system is proposed. Image database used in this study are taken from Wang’s image database
containing 1000 color images. The experiment results show that 2nd level WBCH gives better precision
(0.777) than the other methods, including 1st level WBCH, Color Histogram, Color Co-occurrence Matrix,
and Wavelet texture feature. It can be concluded that the 2nd Level of WBCH can be applied to CBIR system.
Performance Evaluation of Image Edge Detection Techniques CSCJournals
The success of an image recognition procedure is related to the quality of the edges marked. The
aim of this research is to investigate and evaluate edge detection techniques when applied to
noisy images at different scales. Sobel, Prewitt, and Canny edge detection algorithms are
evaluated using artificially generated images and comparison criteria: edge quality (EQ) and map
quality (MQ). The results demonstrated that the use of these criteria can be utilized as an aid for
further analysis and arbitration to find the best edge detector for a given image.
Data Steganography for Optical Color Image CryptosystemsCSCJournals
In this paper, an optical color image cryptosystem with a data hiding scheme is proposed. In the proposed optical cryptosystem, a confidential color image is embedded into the host image of the same size. Then the stego-image is encrypted by using the double random phase encoding algorithm. The seeds to generate random phase data are hidden in the encrypted stego-image by a content-dependent and low distortion data embedding technique. The confidential image and secret data delivery is accomplished by hiding the image into the host image and embedding the data into the encrypted stego-image. Experimental results show that the proposed data steganographic cryptosystem provides large data hiding capacity and high reconstructed image quality.
Text-Image Separation in Document Images using Boundary/Perimeter DetectionIDES Editor
Document analysis plays an important role in office
automation, especially in intelligent signal processing. The
proposed system consists of two modules: block segmentation
and block identification. In this approach, first a document is
segmented into several non-overlapping blocks by utilizing a
novel recursive segmentation technique, and then extracts
the features embedded in each segmented block are extracted.
Two kinds of features, connected components and image
boundary/perimeter features are extracted. Document with
text inside image pose limitations in earlier reported literature.
This is taken care of by applying additional pass of the Run
Length Smearing on the extracted image that contains text.
Proposed scheme is independent of type and language of the
document.
Gabor filter is a powerful way to enhance biometric images like fingerprint images in order to extract correct features from these images, Gabor filter used in extracting features directly asin iris images, and sometimes Gabor filter has been used for texture analysis. In fingerprint images The even symmetric Gabor filter is contextual filter or multi-resolution filter will be used to enhance fingerprint imageby filling small gaps (low-pass effect) in the direction of the ridge (black regions) and to increase the discrimination between ridge and valley (black and white regions) in the direction, orthogonal to the ridge, the proposed method in applying Gabor filter on fingerprint images depending on translated fingerprint image into binary image after applying some simple enhancing methods to partially overcome time consuming problem of the Gabor filter.
Content Based Image Retrieval (CBIR) is one of the
most active in the current research field of multimedia retrieval.
It retrieves the images from the large databases based on images
feature like color, texture and shape. In this paper, Image
retrieval based on multi feature fusion is achieved by color and
texture features as well as the similarity measures are
investigated. The work of color feature extraction is obtained by
using Quadratic Distance and texture features by using Pyramid
Structure Wavelet Transforms and Gray level co-occurrence
matrix. We are comparing all these methods for best image
retrieval
Analysis of combined approaches of CBIR systems by clustering at varying prec...IJECEIAES
The image retrieving system is used to retrieve images from the image database. Two types of Image retrieval techniques are commonly used: content-based and text-based techniques. One of the well-known image retrieval techniques that extract the images in an unsupervised way, known as the cluster-based image retrieval technique. In this cluster-based image retrieval, all visual features of an image are combined to find a better retrieval rate and precisions. The objectives of the study were to develop a new model by combining the three traits i.e., color, shape, and texture of an image. The color-shape and colortexture models were compared to a threshold value with various precision levels. A union was formed of a newly developed model with a color-shape, and color-texture model to find the retrieval rate in terms of precisions of the image retrieval system. The results were experimented on on the COREL standard database and it was found that the union of three models gives better results than the image retrieval from the individual models. The newly developed model and the union of the given models also gives better results than the existing system named clusterbased retrieval of images by unsupervised learning (CLUE).
Query Image Searching With Integrated Textual and Visual Relevance Feedback f...IJERA Editor
There are many researchers who have studied the relevance feedback in the literature of content based image
retrieval (CBIR) community, but none of CBIR search engines support it because of scalability, effectiveness
and efficiency issues. In this, we had implemented an integrated relevance feedback for retrieving of web
images. Here, we had concentrated on integration of both textual features (TF) and visual features (VF) based
relevance feedback (RF), simultaneously we also tested them individually. The TFRF employs and effective
search result clustering (SRC) algorithm to get salient phrases. Then a new user interface (UI) is proposed to
support RF. Experimental results show that the proposed algorithm is scalable, effective and accurated
Efficient fingerprint image enhancement algorithm based on gabor filtereSAT Publishing House
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology
The development of multimedia system technology in Content based Image Retrieval (CBIR) System is
one in every of the outstanding area to retrieve the images from an oversized collection of database. The feature
vectors of the query image are compared with feature vectors of the database images to get matching images.It is
much observed that anyone algorithm isn't beneficial in extracting all differing kinds of natural images. Thus an
intensive analysis of certain color, texture and shape extraction techniques are allotted to spot an efficient CBIR
technique that suits for a selected sort of images. The Extraction of an image includes feature description and
feature extraction. During this paper, we tend to projected Color Layout Descriptor (CLD), grey Level Co-
Occurrences Matrix (GLCM), Marker-Controlled Watershed Segmentation feature extraction technique that
extract the matching image based on the similarity of Color, Texture and shape within the database. For
performance analysis, the image retrieval timing results of the projected technique is calculated and compared
with every of the individual feature.
Experimental Testing Of Partially Encased Composite Beam ColumnsIJERA Editor
The past few decades have seen outstanding advances in the use of composite materials in structural applications. There can be little doubt that, within engineering circles, composites have revolutionized traditional design concepts and made possible an unparalleled range of new and exciting possibilities as viable materials for construction. In addition to the well-known advantages of composite columns, partially encased composite columns offered simplified beam-to-column connection as well as reduced or omitted shuttering thus achieved more cost effective construction. Some companies have patented these new types of partially encased composite column made of light welded steel shapes; moreover, the Canadian Institute of Steel construction CISC has recognized and codified this type of columns. In This paper, Partially Encased Composite Beam Columns is introduced; experimental studies are made on five partially encased beam columns to investigate the behavior of eccentrically loaded partially encased composite columns using different parameters.
Optimization of Polyphenol Content in Green Tea and studying its Antioxidant ...IJERA Editor
The aim of my project is to optimize the level of Polyphenol content present in Green Tea at various
temperatures. During the project various combinations of temperatures and time intervals were used to obtain
the Green Tea extract and the polyphenol content of all these extracts were estimated. Both unfermented and
artificial fermentation condtions were used to obtain the extract. The extracts were further used to screen the
various contents of the extract both normally and after purifying the sample with PVP (Polyvinyl pyrrlidone).
The extract with the highest content of polyphenols were further used to estimate the antioxidant property after
purification with column chromatography.
Survey of Smartphone applications based on OBD-II for Intelligent Transportat...IJERA Editor
Highway transportation is supported with several technologies to decrease risk factors and to obtain secure drive.
With improved software and hardware smartphone technology is able to monitor the useful information from
information network and especially it helps to maintain and control better traffic management for ITS. In this
study accession systems to electronic control unit are examined and also access procedure to vehicle status via
onboard diagnostic (OBD) also demonstrated. Additionally vehicle and environment information evaluation and
prevention of accident risks with smartphone technology are also indicated.
Retention Behavior of Lead Ion in Soil Bentonite LinerIJERA Editor
In this study, it is proposed to obtain breakthrough curves for commonly occurring lead ions in any effluents
through locally available soil amended with 10% bentonite and determine the diffusion coefficients. The
theoretical breakthrough curves of migrating ions in the soil column experiment are generated using
mathematical equation considering effective diffusion coefficients , knowing soil parameters and hydraulic
head. These curves are then compared with experimental curves. In cases where the theoretical and experimental
breakthrough curve do not match, there would be need to consider other parameter retardation factor along with
diffusion coefficient. Theoretical curves are generated for sets of diffusion coefficient and retardation factor.
The sets which give theoretical curve close to experimentally determined breakthrough curves are accepted.
Thus it may be possible to bring out the condition for the dominance of diffusion coefficient and retardation
factor. Then knowing the values of diffusion coefficient and retardation factor along with soil porosity and
hydraulic gradient it is possible to predict the breakthrough times of different ions in the soil. In this work the
breakthrough times of lead ion for the soil of 1m and 0.5m are established. The studies can be extended for any
ion or soil after establishing diffusion coefficient and retardation for the considered ions in the selected liner
under different hydrological regimes.
Performance Analysis of Enhanced Opportunistic Minimum Cost Routingin Mobile ...IJERA Editor
Mobile Ad-Hoc Network (MANET) is a collection of wireless mobile nodes forming a temporary network with
infrastructure less environment to establish a data transmission between nodes within the network. A routing
protocol is used to discover routes between nodes. In this paper, we study the three existing routing protocols
namely AODV, DSDV and DSR to analyze theirperformance based on set of parameters.AODV and DSR
deliver almost all the packets compared to DSDV. Hence we try to modify the AODVprotocol and use in the
cooperative transmission.
In this paper, we study the cooperative transmission at the network layer and cooperative diversity at the
physical layer as a joint optimization of the transmission power in a Mobile Ad-Hoc Network (MANET) with
static channel. However due to variable wireless channels static routing is suboptimal. Proposed protocol
proactively selects forwarding nodes that work cooperatively forwarding the packet towards the destination.
Cooperative transmission side diversity helps in reducing interference. Diversity can be achieved at the physical
layer by coordinating the multiple nodes. Nodes are equipped with Omni-directional antenna and take the
advantages of transmission side diversity to achieve energy saving, under the assumption that channel gains are
available at the transmitters.
The proposed Opportunistic Minimum Cost Cooperative Transmission Shortest Path (OMCTSP) algorithms
select the best optimum route with minimum cost in terms of energy, number of hops, available bandwidth, link
quality (SNR) and outage probability. As the network becomes larger, finding optimal routes becomes
computationally intractable as the complexity of the dynamic programming (DP) approach increases as o (22n)
where n is the number of nodes in the networks. Hence we develop two suboptimal algorithms have complexity
of o (n2) perform as same as optimal algorithm. Also developthe Opportunistic Cooperative Routing in MANET
(O_CORMAN), which is a network layer opportunistic routing scheme for mobile ad hoc networks. Nodes in
the network use the components proactive routing protocol, forwarder list update and local re-transmission. We
evaluate the performance using NS 2.32 simulator there is significant performance improvement with respect to
energy, throughput packet delivery, and delay compared with Modified AODV (OMCTSP).
A Study on Reasons of Attrition and Strategies for Employee RetentionIJERA Editor
The success of any manufacturing organization depends largely on the workers are considered as the backbone
of any company. The study was mainly undertaken to identify the level of employee’s attitude, the
dissatisfaction factors they face in the organization and for what reason they prefer to change their job. Once the
levels of employee’s attitude are identified, it would be possible for the management to take necessary action to
reduce attrition level. Since they are considered as backbone of the company, their progression will lead to the
success of the company for the long run. This study can be helpful in knowing, why the employees prefer to
change their job and which factors make employee dissatisfy. Since the study is critical issue, it is needed by the
originations in order to assess the overall interest and the feelings of the employees towards their Retention.
Learning How to Make Optimal Decisions in Design and Selection of Post-Disast...IJERA Editor
Optimal choice of shelter solutions in post-disaster emergency situations depends on deep understanding of
needs, context of needs, up to date knowledge of the available solutions and smart strategies to connect the two
optimally.
Evidence of needs can be submitted both by the beneficiaries and relief specialists as NGO‟s and the UN. The
solutions can be entered by local or international suppliers. Post-disaster emergency shelter designers are as any
other designer concerned with the ecological, social, cultural and spatial application of technologies to meet
specific human needs after each disaster and in each location. The choice for an on-demand designed postdisaster
shelter contributes to optimal post-disaster shelter relief process and sustainable post-disaster emergency
shelters. The need for qualified engineers who can translate their technical know-how into tailored solutions is
eminent.
In this article we describe a research project that develops and tests a tool for design and selection of on-demand
post-disaster emergency shelters, a Decision Support System (DSS). The tool can be used by the beneficiaries,
relief specialists and politicians. The questions asked by the DSS for gathering evidence on needs and solutions,
can be adapted to each type of user. In addition to assisting relief specialists in decision making, the DSS can be
used as training tool for relief specialists in the field and educating engineers in their thinking.
Study on Theoretical Aspects of Virtual Data Integration and its ApplicationsIJERA Editor
Data integration is the technique of merging data residing at different sources at different locations, and
providing users with an integrated, reconciled view of these data. Such unified view is called global or mediated
schema. It represents the intentional level of the integrated and reconciled data. In the data integration system,
our area of interest in this paper is characterized by an architecture based on a global schema and a set of
sources or source schemas. The objective of this paper is to provide a study on the theoretical aspects of data
integration systems and to present a comprehensive review of the applications of data integration in various
fields including biomedicine, environment, and social networks. It also discusses a privacy framework for
protecting user’s privacy with privacy views and privacy policies.
Mathematical Model for Dynamic Damage Probability of the Repetition Pulse Rat...IJERA Editor
Aimed at the high-energy laser system, under the assumption that the tracking error is the normal stochastic
process of mean square differentiability and ergodicity, the Series Expression of the dynamic damage probability
was given. The example demonstrate some characteristics of the dynamic damage probability as follow. The
system proposed indicates the quantitative relationship between dynamic damage probability and transfer function
of the tracking error system, which offers theoretical and technological support on proofing, designing and testing
the dynamic damage probability of laser system.
Analysis of the Effect of Variation of Baffle Height on the Liquid Sloshing I...IJERA Editor
Sloshing is a common physical phenomenon which occurs in moving tanks with contained liquid masses, such
as liquid cargo carriers, rockets, aircrafts, and the seismically excited storage tanks, dams, reactors, and nuclear
vessels. The sloshing frequencies of contained liquid are essential in the analysis and design of the liquid tanks
and the associated structures. In this paper an attempt made with the VOF model and considered with
immiscible fluids by solving a single set of momentum equations and tracking the volume fraction of each of the
fluids throughout the domain. Further investigated the effect of the vertical baffle heights on the liquid sloshing
in a three-dimensional (3D) rectangular tank. studied dynamic analysis of sloshing in rectangular tanks with
multiple vertical baffles. ANSYS-CFX software was used to study this dynamic analysis subjected to random
excitations including earthquake induced motions. analytically estimated hydrodynamic damping ratio for liquid
sloshing phenomenon in a partially filled rectangular tank for baffles. They used the velocity potential
formulation and linear wave theory for analytic calculations.
FLC-Based DTC Scheme for a New Approach of Two-Leg VSI Fed Induction MotorIJERA Editor
A new Direct Torque Control (DTC) strategy for Induction Motor (IM) drive fed by a two leg three phase
inverter (i.e., Four switches are used in VSI) was proposed in this paper. The proposed methodology is based on
the emulation of operation of the conventional Six-switch three phase inverter. The combination of four
unbalanced voltage vectors is generated by the two-leg three phase inverter, approaching to the synthesis of the
six balanced voltage vectors of the conventional DTC. This approach has been implemented in the design of the
vector selection table of the proposed DTC strategy. Further, Fuzzy Logic Controller (FLC) is proposed in the
speed controller for the improvement of torque ripples. Convention DTC with Six Switch three phase VSI, twoleg
three phase VSI with PI and Fuzzy Controller are implemented using MATLAB/SIMULINK. Simulation
results have shown that the proposed DTC strategy, two-leg inverter fed IM drive revealed an improved
performance.
Low Power and Fast Transient High Swing CMOS Telescopic Operational AmplifierIJERA Editor
CMOS telescopic operational amplifier with high-swing and high-performance is described in this paper. The
swing is attained by using the tail and current source-transistors in deep-linear region. The resultant deprivation
in parameters like differential gain, CMRR and added characteristics are recompensed by using regulatedcascode
differential gain enhancement and a replica-tail feedback technique. Operating at power supply of 3.3V,
the power consumption, slew rate and settling time are improved using transmission controlled pass circuitry
and level amplifier. It is shown through simulations that the Op-Amp preserves its high CMRR and unity gain
frequency.
Studying the Structure and the Optical Properties of Pd Nanoparticles Affecte...IJERA Editor
In this paper, Palladium (Pd) nanoparticales (NPs) at different concentrations (150 and 500) capped with poly
(vinylpyrrolidone) (PVP) were Synthesized by a polyol reduction method in an ethylene glycol solution at
temperature of 45C˚. The structural and optical properties of Pd NPs has been investigated, all thin films were
tested using X-ray diffraction (XRD), all XRD peaks can be indexed as face centered cubic (FCC)
Structure, with strong crystalline orientation at (111) plane. The morphology properties of the prepared films
were study by Atomic Force Microscopy (AFM) the results indicated that all films have nanoscale grain size
around 80 nm and Scan Electron Microscopy (SEM) images show spherical nanoscale particles with clusters
shape. The size of the particles decreased with increasing of concentrations.
An Approach on Determination on Coal Quality using Digital Image ProcessingIJERA Editor
Worldwide coal in the 21st century will be influenced by concerns about the effects of coal combustion on the
local, regional and global environment and on human health. Reliable coal quality data can help decision maker
to better assess the risks and limit the possible environmental degradation and impact on health. Although
millions of coal analysis have been performed worldwide, existing national quality databases are generally of
limited use because much of the data are not readily accessible; geographic coverage are not comprehensive;
analytical data may not be accurate; samples may not be representative, or current. This paper attempts to gives
a fast, accurate, user-friendly and computerized method for analysis of coal quality using techniques of digital
image processing for its better utilization.
On The Transition Probabilities for the Fuzzy States of a Fuzzy Markov ChainIJERA Editor
In this paper the theory of fuzzy logic is mixed with the theory of Markov systems and the abstraction of a
Markov system with fuzzy states introduced. The notions such as fuzzy transient, fuzzy recurrent etc., were
introduced. The results based on these notions are introduced.
Ground Bounce Noise Reduction in Vlsi CircuitsIJERA Editor
Scaling of devices in CMOS technology leads to increase in parameter like Ground bounce
noise, Leakage current, average power dissipation and short channel effect. FinFET are the promising substitute
to replace CMOS. Ground bounce noise is produced when power gating circuit goes from SLEEP to ACTIVE
mode transition. FinFET based designs are compared with MOSFET based designs on basis of different
parameter like Ground bounce noise, leakage current and average power dissipation. HSPICE is the software
tool used for simulation and circuit design.
This section define a level subring or level ideals obtain a set of necessary and sufficient condition for the
equality of two ideals and characterizes field in terms of its fuzzy ideals. It also presents a procedure to construct
a fuzzy subrings (fuzzy ideals) from any given ascending chain of subring ideal. We prove that the lattice of
fuzzy congruence of group G (respectively ring R) is isomorphic to the lattice of fuzzy normal subgroup of G
(respectively fuzzy ideals of R).In Yuan Boond Wu wangrning investigated the relationship between the fuzzy
ideals and the fuzzy congruences on a distributive lattice and obtained that the lattice of fuzzy ideals is
isomorphic to the lattice of fuzzy congruences on a generalized Boolean algebra. Fuzzy group theory can be
used to describe, symmetries and permutation in nature and mathematics. The fuzzy group is one of the oldest
branches of abstract algebra. For example group can be used is classify to all of the forms chemical crystal can
take. Group can be used to count the number of non-equivalent objects and permutation or symmetries. For
example, the number of different is switching functions of n, variable when permutation of the input are
allowed. Beside crystallography and combinatory group have application of quantum mechanics.
With the coastal population increasing, storms have been inflicting unprecedented losses on coastal
communities. Coastal agencies require advance information on the predicted path, intensity and progress of a
storm and associated waves and storm surges;
Near-real-time information during the peak of the storm to monitor flooding and control rescue operations; And
post storm reports to assess the damage and plan the recovery. The same holds true for other disasters, such as
oil spills and algal blooms. Coastal communities are also facing a rising sea level, caused mainly by global
warming. Airborne and satellite remote sensors, such as multispectral imagers, LIDAR and RADAR, are now
able to provide Most of the information required for emergency response and coastal management.
The idea of backpacking is just amazing but packing is quite stressful especially for a fashionista. Minimalistic packing is what I advocate for.Here is a simple packing list every woman can use.
Propose shot boundary detection methods by using visual hybrid featuresIJECEIAES
Shot boundary detection is the fundamental technique that plays an important role in a variety of video processing tasks such as summarization, retrieval, object tracking, and so on. This technique involves segmenting a video sequence into shots, each of which is a sequence of interrelated temporal frames. This paper introduces two methods, where the first is for detecting the cut shot boundary via employing visual hybrid features, while the second method is to compare between them. This enhances the effectiveness of the performance of detecting the shot by selecting the strongest features. The first method was performed by utilizing hybrid features, which included statistics histogram of hue-saturation-value color space and grey level co-occurrence matrix. The second method was performed by utilizing hybrid features that include discrete wavelet transform and grey level co-occurrence matrix. The frame size decreased. This process had the advantage of reducing the computation time. Also used local adaptive thresholds, which enhanced the method’s performance. The tested videos were obtained from the BBC archive, which included BBC Learning English and BBC News. Experimental results have indicated that the second method has achieved (97.618%) accuracy performance, which was higher than the first and other methods using evaluation metrics.
TEXT DETECTION AND EXTRACTION FROM VIDEOS USING ANN BASED NETWORKijscai
With fast intensification of existing multimedia documents and mounting demand for information indexing and retrieval, much endeavor has been done on extracting the text from images and videos. The prime intention of the projected system is to spot and haul out the scene text from video. Extracting the scene text from video is demanding due to complex background, varying font size, different style, lower resolution and blurring, position, viewing angle and so on. In this paper we put forward a hybrid method where the two most well-liked text extraction techniques i.e. region based method and connected component (CC) based method comes together. Initially the video is split into frames and key frames obtained. Text region indicator (TRI) is being developed to compute the text prevailing confidence and
candidate region by performing binarization. Artificial Neural network (ANN) is used as the classifier and Optical Character Recognition (OCR) is used for character verification. Text is grouped by constructing the minimum spanning tree with the use of bounding box distance.
A Survey On Thresholding Operators of Text Extraction In VideosCSCJournals
ideo indexing is an important problem that has interested by the communities of visual information in image processing. The detection and extraction of scene and caption text from unconstrained, general purpose video is an important research problem in the context of content-based retrieval and summarization. In this paper, the technique presented is for detection text from frames video. Finding the textual contents in images is a challenging and promising research area in information technology. Consequently, text detection and recognition in multimedia had become one of the most important fields in computer vision due to its valuable uses in a variety of recent technical applications. The work in this paper consists using morphological operations for extract text appearing in the video frames. The proposed scheme well as preprocessing to differentiate among where it as the high similarity between text and background information. Experimental results show that the resultant image is the image with only text. The evaluated criteria are applied with the image result and one obtained bay different operator.
A Survey On Thresholding Operators of Text Extraction In VideosCSCJournals
Video indexing is an important problem that has interested by the communities of visual information in image processing. The detection and extraction of scene and caption text from unconstrained, general purpose video is an important research problem in the context of content-based retrieval and summarization. In this paper, the technique presented is for detection text from frames video. Finding the textual contents in images is a challenging and promising research area in information technology. Consequently, text detection and recognition in multimedia had become one of the most important fields in computer vision due to its valuable uses in a variety of recent technical applications. The work in this paper consists using morphological operations for extract text appearing in the video frames. The proposed scheme well as preprocessing to differentiate among where it as the high similarity between text and background information. Experimental results show that the resultant image is the image with only text. The evaluated criteria are applied with the image result and one obtained bay different operator.
A binarization technique for extraction of devanagari text from camera based ...sipij
This paper presents a binarization method for camera based natural scene (NS) images based on edge
analysis and morphological dilation. Image is converted to grey scale image and edge detection is carried
out using canny edge detection. The edge image is dilated using morphological dilation and analyzed to
remove edges corresponding to non-text regions. The image is binarized using mean and standard
deviation of edge pixels. Post processing of resulting images is done to fill gaps and to smooth text strokes.
The algorithm is tested on a variety of NS images captured using a digital camera under variable
resolutions, lightening conditions having text of different fonts, styles and backgrounds. The results are
compared with other standard techniques. The method is fast and works well for camera based natural
scene images.
Modified Skip Line Encoding for Binary Image Compressionidescitation
Image Compression is an important issue in
Internet, mobile communication, digital library, digital
photography, multimedia, teleconferencing and other
applications. Application areas of Image Compression would
focus on the problem of optimizing storage space and
transmission bandwidth. In this paper, a modified form of skip
line encoding is proposed to further reduce the redundancy in
the image. The performance is found to be better than the
skip-line encoding.
Improved nonlocal means based on pre classification and invariant block matchingIAEME Publication
One of the most popular image denoising methods based on self-similarity is called nonlocal
means (NLM). Though it can achieve remarkable performance, this method has a few shortcomings,
e.g., the computationally expensive calculation of the similarity measure, and the lack of reliable
candidates for some non repetitive patches. In this paper, we propose to improve NLM by integrating
Gaussian blur, clustering, and row image weighted averaging into the NLM framework.
Experimental results show that the proposed technique can perform denoising better than the original
NLM both quantitatively and visually, especially when the noise level is high.
Performance of Efficient Closed-Form Solution to Comprehensive Frontier Exposureiosrjce
IOSR Journal of Electronics and Communication Engineering(IOSR-JECE) is a double blind peer reviewed International Journal that provides rapid publication (within a month) of articles in all areas of electronics and communication engineering and its applications. The journal welcomes publications of high quality papers on theoretical developments and practical applications in electronics and communication engineering. Original research papers, state-of-the-art reviews, and high quality technical notes are invited for publications.
Welcome to WIPAC Monthly the magazine brought to you by the LinkedIn Group Water Industry Process Automation & Control.
In this month's edition, along with this month's industry news to celebrate the 13 years since the group was created we have articles including
A case study of the used of Advanced Process Control at the Wastewater Treatment works at Lleida in Spain
A look back on an article on smart wastewater networks in order to see how the industry has measured up in the interim around the adoption of Digital Transformation in the Water Industry.
Final project report on grocery store management system..pdfKamal Acharya
In today’s fast-changing business environment, it’s extremely important to be able to respond to client needs in the most effective and timely manner. If your customers wish to see your business online and have instant access to your products or services.
Online Grocery Store is an e-commerce website, which retails various grocery products. This project allows viewing various products available enables registered users to purchase desired products instantly using Paytm, UPI payment processor (Instant Pay) and also can place order by using Cash on Delivery (Pay Later) option. This project provides an easy access to Administrators and Managers to view orders placed using Pay Later and Instant Pay options.
In order to develop an e-commerce website, a number of Technologies must be studied and understood. These include multi-tiered architecture, server and client-side scripting techniques, implementation technologies, programming language (such as PHP, HTML, CSS, JavaScript) and MySQL relational databases. This is a project with the objective to develop a basic website where a consumer is provided with a shopping cart website and also to know about the technologies used to develop such a website.
This document will discuss each of the underlying technologies to create and implement an e- commerce website.
About
Indigenized remote control interface card suitable for MAFI system CCR equipment. Compatible for IDM8000 CCR. Backplane mounted serial and TCP/Ethernet communication module for CCR remote access. IDM 8000 CCR remote control on serial and TCP protocol.
• Remote control: Parallel or serial interface.
• Compatible with MAFI CCR system.
• Compatible with IDM8000 CCR.
• Compatible with Backplane mount serial communication.
• Compatible with commercial and Defence aviation CCR system.
• Remote control system for accessing CCR and allied system over serial or TCP.
• Indigenized local Support/presence in India.
• Easy in configuration using DIP switches.
Technical Specifications
Indigenized remote control interface card suitable for MAFI system CCR equipment. Compatible for IDM8000 CCR. Backplane mounted serial and TCP/Ethernet communication module for CCR remote access. IDM 8000 CCR remote control on serial and TCP protocol.
Key Features
Indigenized remote control interface card suitable for MAFI system CCR equipment. Compatible for IDM8000 CCR. Backplane mounted serial and TCP/Ethernet communication module for CCR remote access. IDM 8000 CCR remote control on serial and TCP protocol.
• Remote control: Parallel or serial interface
• Compatible with MAFI CCR system
• Copatiable with IDM8000 CCR
• Compatible with Backplane mount serial communication.
• Compatible with commercial and Defence aviation CCR system.
• Remote control system for accessing CCR and allied system over serial or TCP.
• Indigenized local Support/presence in India.
Application
• Remote control: Parallel or serial interface.
• Compatible with MAFI CCR system.
• Compatible with IDM8000 CCR.
• Compatible with Backplane mount serial communication.
• Compatible with commercial and Defence aviation CCR system.
• Remote control system for accessing CCR and allied system over serial or TCP.
• Indigenized local Support/presence in India.
• Easy in configuration using DIP switches.
NO1 Uk best vashikaran specialist in delhi vashikaran baba near me online vas...Amil Baba Dawood bangali
Contact with Dawood Bhai Just call on +92322-6382012 and we'll help you. We'll solve all your problems within 12 to 24 hours and with 101% guarantee and with astrology systematic. If you want to take any personal or professional advice then also you can call us on +92322-6382012 , ONLINE LOVE PROBLEM & Other all types of Daily Life Problem's.Then CALL or WHATSAPP us on +92322-6382012 and Get all these problems solutions here by Amil Baba DAWOOD BANGALI
#vashikaranspecialist #astrologer #palmistry #amliyaat #taweez #manpasandshadi #horoscope #spiritual #lovelife #lovespell #marriagespell#aamilbabainpakistan #amilbabainkarachi #powerfullblackmagicspell #kalajadumantarspecialist #realamilbaba #AmilbabainPakistan #astrologerincanada #astrologerindubai #lovespellsmaster #kalajaduspecialist #lovespellsthatwork #aamilbabainlahore#blackmagicformarriage #aamilbaba #kalajadu #kalailam #taweez #wazifaexpert #jadumantar #vashikaranspecialist #astrologer #palmistry #amliyaat #taweez #manpasandshadi #horoscope #spiritual #lovelife #lovespell #marriagespell#aamilbabainpakistan #amilbabainkarachi #powerfullblackmagicspell #kalajadumantarspecialist #realamilbaba #AmilbabainPakistan #astrologerincanada #astrologerindubai #lovespellsmaster #kalajaduspecialist #lovespellsthatwork #aamilbabainlahore #blackmagicforlove #blackmagicformarriage #aamilbaba #kalajadu #kalailam #taweez #wazifaexpert #jadumantar #vashikaranspecialist #astrologer #palmistry #amliyaat #taweez #manpasandshadi #horoscope #spiritual #lovelife #lovespell #marriagespell#aamilbabainpakistan #amilbabainkarachi #powerfullblackmagicspell #kalajadumantarspecialist #realamilbaba #AmilbabainPakistan #astrologerincanada #astrologerindubai #lovespellsmaster #kalajaduspecialist #lovespellsthatwork #aamilbabainlahore #Amilbabainuk #amilbabainspain #amilbabaindubai #Amilbabainnorway #amilbabainkrachi #amilbabainlahore #amilbabaingujranwalan #amilbabainislamabad
Governing Equations for Fundamental Aerodynamics_Anderson2010.pdf
A Framework for Curved Videotext Detection and Extraction
1. Sudir.P Int. Journal of Engineering Research and Applications www.ijera.com
ISSN: 2248-9622, Vol. 6, Issue 1, (Part – 3) January 2016, pp.01-06
www.ijera.com 1|P a g e
A Framework for Curved Videotext Detection and Extraction
Sudir.Pa
, M.Ravishankarb
a
Asst.professor,Dept of E&C,SJCIT,Chikkaballapur,India
b
Principal,VVIT,Mysore,India
Abstract
Proposed approach explores a new framework for curved video text detection and extraction. The algorithm first
utilizes a Gaussian filter based Color Edge Enhancement followed by a Gray level Co-occurrence matrix feature
extraction method for text detection. Secondly, a Connected Component filtering method is utilized to generate
clear localization result and at last, a Round Scan method is performed to extract curved text and generate binary
result for recognition by OCR. Experiments on various curved video data and Hua’s horizontal video text
dataset shows the effectiveness and robustness of the proposed method.
Keywords:Curve Video text;Gaussian Filter;Gray level Co-occurrence matrix;Round scan Method.
I. Introduction
Due to tremendous advancement in Video
technology, copious amount of video information
available calls for the need for Semantic Video
analysis and management. Since Video text is
important supplemental content information, some
of the Video processing techniques focus on text
data embedded in videos. Video text detection and
extraction is a vital task for applications such as
Video Indexing and Content based video retrieval.
Videotexts are classified into two types, first is
Superimposed Text which is added as a part of
editing process and the second is Scene text which
appears naturally in a Scene captured by a camera.
Although many methods exist, text detection and
extraction is still a challenging task because of
unconstrained colors, sizes, and alignments of the
characters. Text detection and extraction methods
can be divided into three subgroups: Connected
Component (CC), Edge based and Texture-based.
CC-based methods [1][2] groups small components
into successively larger ones until all regions are
identified in the image.CC-methods fail when text in
video frame has low contrast and Non-Uniform
Color. Edge based approach [3][4][5] requires text to
have a better contrast to the background in order to
detect the edges. So these methods exhibit poor
result in case of complex backgrounds. Texture
based methods [6][7] utilize various local texture
descriptors, such as Gabor Filter[8] and Wavelet
Filters [9].Since almost all of these methods rely on
horizontal or Vertical alignment of Video text they
fail in the case of Multi Oriented Video Texts.
Recently some efficient algorithms have proposed
specifically for Multi Oriented Video Texts.
Shivakumara et al.[10] proposed a method for
detecting arbitrarily oriented text based on
Morphological approach but the method fails in case
of complex background. Yong et al.[11] proposed a
corner and skeleton based method for arbitrarily
oriented text which is quiet robust only when the
corners are detected effectively. It fails in case of
low resolution Videos. Shivakumara et al. [12]
proposed an arbitrarily oriented scene text detection
method which extracts text lines of any orientation
based on Gradient Vector Flow (GVF) and Neighbor
component grouping. However the proposed method
does not give good accuracy for less spaced text
lines. Shivakumara et al. [13] proposed a curved text
detection scheme which uses enhancement criterion
and quad tree approach. Although efficient in
detection proposed method fails to eliminate false
positives. Clearly all of the above methods though
efficient in detection fail to produce an OCR ready
input. Hence in this paper an efficient text detection
and extraction scheme is proposed for Curved
Videotexts. The main contributions of the proposed
method are as follows: 1) A Gaussian Filter based
Video frame Enhancement Model 2) A Gray level
Co-occurrence matrix feature extraction method for
text detection 3) A Round scan method for partial
and fully circular videotext recognition is proposed
which segments curve texts and produces binarized
text segments for recognition by OCR.
II. Proposed Method
The proposed method consists of three steps:
Filter based Color edge enhancement, Text detection
by Extracting Standard deviation as feature from
block wise Gray level Co-occurrence matrix
generated, A Round scan method for circular and
semicircular text extraction.
2.1 Gaussian Filter based Color Edge
Enhancement
The purpose of use of text edge enhancement
procedure is to highlight fine detail in an image or to
restore, at least partially, text detail that has been
RESEARCH ARTICLE OPEN ACCESS
2. Sudir.P Int. Journal of Engineering Research and Applications www.ijera.com
ISSN: 2248-9622, Vol. 6, Issue 1, (Part – 3) January 2016, pp.01-06
www.ijera.com 2|P a g e
blurred. Text Edge enhancement involves
sharpening the text edges with respect to their
background. In the proposed method first each set of
R, G and B-bands are smoothed by a 3x3 Gaussian
kernel. The reason for choosing Gaussian kernel is
that it is an efficient filter for removing noise drawn
from a normal distribution and Gaussian functions
are rotationally symmetric in two dimensions hence
it will not bias subsequent edge detection in any
particular direction. The degree of smoothening is
governed by variance s. A larger s implies a wider
Gaussian filter and greater smoothening. The
Gaussian filter in the continuous space is given b
2
2
2
2
22
2
1
2
1
),(
nm
eenmh
(1)
Let Ix be original band where x ∈ (r, g, b) and Jx be
the Gaussian filter smoothed band. Then the
enhanced band Ex is given by the formula.
Ex=(1+A)Ix-AJx (2)
Where A is an Amplification factor (A=1 and σ=5 in
our experiment). Let F be the Edge Enhanced Video
frame obtained by concatenating Er ,E g and Eb. The
result obtained after the enhancement procedure is
shown in Fig.1(b).
2.2 Text detection method
Proposed approach which is texture-based is based
on the a statistical method of examining texture that
considers the spatial relationship of pixels which is
the gray-level co-occurrence matrix (GLCM), also
known as the gray-level spatial dependence matrix.
The GLCM functions characterize the texture of an
image by calculating how often pairs of pixel with
specific values and in a specified spatial relationship
occur in an image, creating a GLCM, and then
extracting statistical measures from this matrix.
Given an image I, of size M×M, the co-occurrence,
matrix G can be defined as
(3)
Here, the offset (Δx, Δy) specifies the distance
between the pixel-of-interest and its neighbour. The
offset (Δx, Δy) parameterization makes the co-
occurrence matrix sensitive to rotation. Choosing an
offset vector, such that the rotation of the image is
not equal to 180 degrees, will result in a different co-
occurrence matrix for the rotated image. Standard
deviation feature is extracted from 4 gray co-
occurrence matrix at 4 different rotations given by
[0 Δ] for 0◦: G horizontal, [-Δ, Δ] for 45◦: G right
diagonal, [-Δ 0] for 90◦: G vertical, and [-Δ − Δ] for
135◦: G left diagonal.
The input video frame is partitioned into n2
number
of blocks. For each block B,let B(i,j) be the (i,j)th
entry in a normalized GLCM. The mean and
standard deviations for the rows and columns of the
matrix are
𝜇 𝑥 = 𝑖. 𝐵(𝑖, 𝑗)𝑗𝑖 , 𝜇 𝑦 = 𝑗. 𝐵(𝑖, 𝑗)𝑗𝑖 (4)
𝜎𝑥 = 𝑖 − 𝜇 𝑥
2
𝐵(𝑖, 𝑗)𝑗𝑖 , 𝜎𝑦 = 𝑗 − 𝜇 𝑦
2
𝐵(𝑖, 𝑗)𝑗𝑖
(5)
Standard deviation for every block for all four
rotations are calculated and the maximum value
among all these are considered. The standard
deviation feature value are threshold by Otsu’s
method [14], which chooses the threshold to
minimize the interclass variance of the black and
white pixels. The result is a black and white image
where white color signifies probable text regions.
The block in the original image F is retained as it is
if its corresponding threshold image value is 1 else
the block is suppressed by assigning 0 to all the
pixels in the block. The resultant image is shown in
Fig.1(c).
f(x,y)={
(6)
2.3 False Positive removal method
False Positive elimination is executed based on size
of CC and height of CC since it is a known fact that
all the characters in a circular text will be of almost
of same height. Height of a CC of circular text is
chosen as maximum among length of CC and width
of CC. In our experiment we ignore CCs whose size
is less than 200 and height less than 20 and height
greater than 70.The result of false positive
elimination is shown in Fig.1 (e, k, l, m, n, o).
f(x,y) if B(i,j)=1
0 otherwise
𝐺 𝑖, 𝑗 =
1 𝐼 𝑥 + ∆𝑥, 𝑦 + ∆𝑦 = 𝑗
0 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒
𝑀
𝑦=1
𝑀
𝑥=1
3. Sudir.P Int. Journal of Engineering Research and Applications www.ijera.com
ISSN: 2248-9622, Vol. 6, Issue 1, (Part – 3) January 2016, pp.01-06
www.ijera.com 3|P a g e
Fig.1. Curved Text Detection and Localization result (a,f,g,h,i,j)-Video Frame b. Enhanced Frame (c) Text Detection result without
Enhancement (d) text detection result with enhancement (e,k,l,m,n,o)- Result after False positive elimination
2.4 Text Extraction and recognition procedure
The proposed procedure aims to extract the curve text for recognition using OCR from the result obtained after
false positive elimination. Two types of curve texts have to be dealt with for segmentation; the first case is
where the curve text covers more than 75% of the frame which we call as fully circular text (Fig.2e) and curve
text which covers less than 50% of the frame which we call as partial circular text (Fig.2g). In order to segment
in both cases one needs to find a origin point of scan. The procedure to find origin point of scan is as follows:
Fully Circular text: Obtain Horizontal projection as shown in Fig.2c.Find first non zero X-axes
value(X1) by scanning X-axes value from left to right and first nonzero X-axes value(X2) by scanning
X-axes value from right to left. Similarly obtain Vertical projection and find first nonzero Y-axes value
(Y1) by scanning Y-axes value from top left to bottom and first non zero Y-axes value (Y2) by
scanning Y-axes value from bottom to right as shown in Fig.2b. Origin point of scan C(x, y) is found
by using the formula and is shown in Fig.2e.
2
12 XX
x
and
2
12 YY
y
(7)
Partially Circular text: Choose a Coordinate manually as Origin point of scan C(x, y) such that it is at
equidistant from the centroid of all CCs as shown in Fig.2h.
Round scan method: In order to extract curved text first the Origin point of scan is chosen and an extreme point
A (i, j) is found at a distance β chosen heuristically so as to cover entire text region. All the pixel points on the
linear path from C(x1, y1) to A(xi, yi) is extracted and stored as shown in Fig.2a. The next point A1(x, y) is found
as per equation 10 and again all pixel values are extracted and stored.
x=x1-βsin(απ/180), y=y1-βsin(απ/180), (8)
Above procedure is repeated for full 3600
as shown in fig.2f by finding new extreme points and all the pixels in
the path from origin point of scan to extreme points are extracted and stored and the resultant image obtained are
shown in Fig.2.
Fig.2. (a) Extract each scan line pixel values (b) to find new scan line (c) Horizontal Projection (d)Vertical
Projection (e) Origin point of scan (f) Scan lines (g) Origin point of scan (h) Scan lines
Recognition of curved text in Video frames is a challenging task due to complex background and arbitrary
orientations. There are few methods [16, 17, 18] which extract curved text from natural scene images. However,
the scope of these methods is limited to image text detection and extraction but not binarization and recognition.
4. Sudir.P Int. Journal of Engineering Research and Applications www.ijera.com
ISSN: 2248-9622, Vol. 6, Issue 1, (Part – 3) January 2016, pp.01-06
www.ijera.com 4|P a g e
Shivakumara et al [18] present a novel method of multi oriented text recognition in scene images using HMM
and performs segmentation free recognition in curved text image. Proposed method is the first of its kind which
linearizes and binarizes the curve Video text and provides input to OCR for recognition. The extracted text
using Round scan method is binarized using Otsu Threshold and Recognized using Tesseract OCR [19]. Sample
results are shown in Fig.3.
Fig.3. Sample Curved Text Extraction and Recognition results
III. Results
The proposed approach has been tested on 20 mpeg-1 video frames with 320x240 pixel resolution as there is no
benchmarked dataset on Curved video text data, available in the literature. It contains 92 words and 670
characters. We also use a small dataset of 45 video frames, which is available, publicly [10] to evaluate the
performance of the method. We choose four methods for comparison of which first is a recently developed
method by Shivakumara et al.[13] which address curved text detection in video through an enhancement
criterion and use of quad tree. Second is Laplacian method [10] which works well for non-horizontal Video text
by combining Laplacian and Fourier. Third is Bayesian method [21] which explores Bayesian classifier and
gradient. Fourth is a method for arbitrary text detection by Sharma et al. [16] which proposes gradient directions
and two stage grouping. Following performance criterion has been defined for horizontal, vertical and
multioriented videotext (except curved text).
Truly Detected Block (TDB): A detected block that contains at least one true character. Thus, a TDB
may or may not fully enclose a text line.
Falsely Detected Block (FDB): A detected block that does not contain text.
Text Block with Missing Data (MDB): A detected block that misses more than 20% of the characters
of a text line (MDB is a subset of TDB).
The performance measures are defined as follows.
ATB
TDB
Rcall )(Re)1
FDBTDB
TDB
Pecision
)(Pr)2
RP
PR
FmeasureF
2
)()3
(9)
Average Processing Time (APT) per frame is also considered as a measure to evaluate the proposed
method.
1.1. Performances on Hua’s data
A sample frame from Hua’s data is shown in Fig.1(i,j) and the text detection results of the proposed method for
the frame in Fig.1(n,o).The proposed method detected almost all text properly. The Comparison results of the
proposed method and existing method are reported in Table 1. The results show that our method is robust to the
orientation, perspective, color, and lighting of the text object. It detected most text objects successfully.
1.2. Performance Analysis on Curved data
Sample results of the proposed method for curved text extraction versus the Quad tree based method is shown in
Fig.4 where (a,d,g) shows input frames having different background and fonts and (b,e,h) shows the results
given by the proposed method and (c,f,i) shows the result for the Quad tree based method. Fig.4 shows that the
proposed method extracts curved text successfully. Table 1 and 2 show that the proposed method outperforms
the existing methods in terms of recall, precision-measure and misdetection rate. The main reason for poor
results of the existing methods is that the existing methods are developed for horizontal and non-horizontal text
detection but not for curved video text detection. Table 3 shows the recognition accuracy obtained on the curved
dataset. The Accuracy is fairly good and there is still scope for improvement in this regard.
5. Sudir.P Int. Journal of Engineering Research and Applications www.ijera.com
ISSN: 2248-9622, Vol. 6, Issue 1, (Part – 3) January 2016, pp.01-06
www.ijera.com 5|P a g e
Fig.4. Text Detection result (a,d,g) Input Frames,(b,e,h) Proposed method result,(c,f,i) Quad tree based method
Table 1. Comparison of proposed method with Existing Detection Methods for Hua’s database
Methods R P F MDR APT(secs)
Proposed 0.87 0.9 0.9 0.06 1.7
Quad tree 0.82 0.88 0.84 0.06 2.0
Sharma 0.88 0.77 0.82 0.32 9.0
Bayesian 0.87 0.85 0.85 0.18 5.6
Laplacian 0.93 0.81 0.87 0.07 11.7
Table 2. Performance of the Proposed and Existing Detection Methods on Curved Data
Methods R P F MDR APT(secs)
Proposed 0.82 0.87 0.84 0.20 1.7
Quad tree 0.80 0.83 0.81 0.25 2.3
Sharma 0.73 0.88 0.79 0.28 10.3
Bayesian 0.59 0.52 0.55 0.27 12.1
Laplacian 0.55 0.68 0.60 0.42 9.9
Table 3. Character and Word Recognition Performance by Proposed Recognition Method
IV. Conclusion
In this paper a novel method is proposed for curved video text detection and extraction which uses the
standard Deviation feature embodied in Gray Co-occurrence matrix obtained from Gaussian filter enhanced
Video frame. A Novel Round Scan method is performed to extract curved text and generate binary result for
recognition by OCR. Some experimental results and performance comparisons with standard methods are
reported in detail, thereby confirming that our method is capable of robustly handling Curved video text. Our
future study will mostly be focusing increasing Curved video text recognition rate.
References
[1] A.K. Jain and B. Yu. (1998) Automatic Text Location in Images and Video Frames, Pattern Recognition,Vol.31 (12), pp. 2055-2076.
[2] Lienhart,R., Stuber,F.Automatic.(1996).Text Recognition in Digital Videos, Proceedings of SPIE Image and VideoProcessing IV
2666, pp. 180-188.
[3] Agnihotri,L., Dimitrova,N.(1999)Text Detection for Video Analysis, IEEE Workshop on CBAIVL, pp. 109113.
[4] Agnihotri,L., Dimitrova,N., Soletic,(2002),M.Multi-layered Videotext Extraction Method, IEEE International Conference on
Multimedia and Expo (ICME), Lausanne (Switzerland), August 26-29, 2002.
[5] Hua,X.-S., Chen, X.-R. et al.(2001).Automatic Location of Text in Video Frames, Intl Workshop on Multimedia Information
Retrieval In conjunction with ACM Multimedia.
[6] Kim, H-K. et al.(1996).Efficient Automatic Text Location Method and Content-based Indexing and Structuring of Video Database,
Journal of Visual Communication and Image Representation, vol.7,No.4, pp.336-344.
[7] Li,H., Doermann,D, Kia,O.(2000).Automatic Text Detection and Tracking in Digital Video, IEEE Trans. on Image processing.vol.9,
No.1, pp. 147-155.
Dataset Accuracy
Character Word
Own Curved Data 49 43
6. Sudir.P Int. Journal of Engineering Research and Applications www.ijera.com
ISSN: 2248-9622, Vol. 6, Issue 1, (Part – 3) January 2016, pp.01-06
www.ijera.com 6|P a g e
[8] Jain,A.K., Bhatarcharjee,S.(1992).Text Segmentation using Gabor Filters for automatic document processing, Machine Vision
and Application, vol.5 pp. 169 -184.
[9] Li,H., Doermann,D, Kia,O.(1998).Automatic Text Detection and Tracking in Digital Video, Univ. of Maryland, College Park,
Tech.Reps. LAMP-TR-028, CAR-TR-900.
[10] P. Shivakumara, T. Q. Phan and C. L. Tan.(2011).A Laplacian Approach to Multi-Oriented Text Detection in Video, IEEE Trans. on
PAMI, pp. 412-419.
[11] Yong Zhang, Jianhuang Lai.(2012) Arbitrarily Oriented Text Detection Using Geodesic Distances Between Corners and Skeletons,
1st International Conference on Pattern Recognition (ICPR ),Tsukuba, Japan.
[12] Palaiahnakote Shivakumara, Trung Quy Phan, Shijian Lu and Chew Lim Tan.(2013).Gradient Vector Flow and Grouping based
Method for Arbitrarily Oriented Scene text Detection in Video Images, Circuits and Systems for Video Technology, IEEE
Transactions on ,Volume:23 , Issue: 10.
[13] P.Shivakumara, H.T.Basavaraju, D.S.Guru, and C. L.Tan.(2013).Detection of Curved Text in Video: Quad Tree based Method,
ICDAR.
[14] N. Otsu.A.(1979). Threshold Selection Method from GrayLevel Histograms, IEEE Trans. on Systems, Man, and Cybernetics, Vol.
9,, pp. 62-66.
[15] H.K. Koh, W. Shen, B. Shuter and A.A. Kassim.(2009).Segmentation of kidney cortex in MRI studies: a constrained morphological
3D h-maxima transform approach,International Journal of Medical Engineering and Informatics, Vol. 1, No. 3, pp. 330-341.
[16] N. Sharma, P. Shivakumara, U. Pal, M. Bluemenstein and C. L. Tan.(2012).A New Method for Arbitrarily-Oriented Text Detection
in Video, In Proc. DAS, pp. 74-78.
[17] C. Yao, X. Bai, W. Liu, Y. Ma and Z. Tu.(2012).Detecting Texts of Arbitrary Orientations in Natural Images,CVPR.
[18] Sangheeta Roy, Partha Pratim Roy, Palaiahnakote Shivakumara, Umapada Pal ,Chew Lim Tan, (ACPR2013).HMM based Multi
Oriented Text Recognition in Natural Scene Image, The 2nd Asian Conference on Pattern Recognition.
[19] http://code.google.com/p/tesseract-ocr/
[20] X. S Hua, L. Wenyin and H.J. Zhang.(2004).An Automatic Performance Evaluation Protocol for Video Text Detection
Algorithms, IEEE Trans. on CSVT, 498-507.
[21] P. Shivakumara, R. P. Sreedhar, T. Q. Phan, S. Lu and C. L. Tan.(2012).Multi-Oriented Video Scene Text Detection through
Bayesian Classification and Boundary Growing,IEEE Trans. on CSVT,1227-1235.