Pub Date : 2013-12-01DOI: 10.1109/NCVPRIPG.2013.6776227
N. Sanket, K. Manikantan, S. Ramachandran
Face Localization on frontal pose grayscale images under varying conditions of illumination, background and gender is challenging. Developing a robust technique to handle all the aforementioned variations requires a lot of training time and hardware to obtain a good localization rate. In this paper, a novel Recursive Binary Particle Swarm Optimization is proposed, to create a generic template of the face. This template is then used for template matching in the Block DCT Signal Space to obtain the position of the face in the test image. Experimental results, obtained by applying the proposed algorithm on CalTech, FERET and Extended Yale B face databases, show that the proposed system provides good localization rates with a low training time.
{"title":"Recursive Binary Particle Swarm Optimization based Face Localization","authors":"N. Sanket, K. Manikantan, S. Ramachandran","doi":"10.1109/NCVPRIPG.2013.6776227","DOIUrl":"https://doi.org/10.1109/NCVPRIPG.2013.6776227","url":null,"abstract":"Face Localization on frontal pose grayscale images under varying conditions of illumination, background and gender is challenging. Developing a robust technique to handle all the aforementioned variations requires a lot of training time and hardware to obtain a good localization rate. In this paper, a novel Recursive Binary Particle Swarm Optimization is proposed, to create a generic template of the face. This template is then used for template matching in the Block DCT Signal Space to obtain the position of the face in the test image. Experimental results, obtained by applying the proposed algorithm on CalTech, FERET and Extended Yale B face databases, show that the proposed system provides good localization rates with a low training time.","PeriodicalId":436402,"journal":{"name":"2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)","volume":"558 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131858111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/NCVPRIPG.2013.6776254
C. Fasil, C. Jiji
Motion blur due to camera shake during exposure often leads to noticeable artifacts in images. In this paper, we address the problem of recovering the true image from its blurred version. The problem is challenging since both the blur kernel and the sharp image are unknown. The quality of a deblurred image is closely related to the correctness of the estimated blur kernel. In this work we focus on the use of Radon Transform for blur kernel estimation. It is done by analyzing edges in the blurred image and there by constructing the projections of the blur kernel. Estimation of the blur kernel from its projections is done by incorporating the sparse nature of the blur kernel. The problem is solved through l1 minimization making use of the estimated projections. After building the kernel, we use a non-blind deconvolution algorithm for producing the sharp image. Results show that this approach is well suited for blurred images having significant edges.
{"title":"Kernel estimation from blurred edge profiles using Radon Transform for shaken images","authors":"C. Fasil, C. Jiji","doi":"10.1109/NCVPRIPG.2013.6776254","DOIUrl":"https://doi.org/10.1109/NCVPRIPG.2013.6776254","url":null,"abstract":"Motion blur due to camera shake during exposure often leads to noticeable artifacts in images. In this paper, we address the problem of recovering the true image from its blurred version. The problem is challenging since both the blur kernel and the sharp image are unknown. The quality of a deblurred image is closely related to the correctness of the estimated blur kernel. In this work we focus on the use of Radon Transform for blur kernel estimation. It is done by analyzing edges in the blurred image and there by constructing the projections of the blur kernel. Estimation of the blur kernel from its projections is done by incorporating the sparse nature of the blur kernel. The problem is solved through l1 minimization making use of the estimated projections. After building the kernel, we use a non-blind deconvolution algorithm for producing the sharp image. Results show that this approach is well suited for blurred images having significant edges.","PeriodicalId":436402,"journal":{"name":"2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115929963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/NCVPRIPG.2013.6776201
Swapna Agarwal, D. Mukherjee
In recent years the need of a robust facial component tracking especially lip tracking algorithm has increased dramatically. We implement an active contour (snake) model inspired by human perception for lip tracking. In addition to the conventional energy terms for tension, rigidity (internal energy) and gradient magnitude (external energy) we propose to include energy terms from domain knowledge for lip shape constraint and local region profile constraint. Generalized deterministic annealing (GDA) update of the energy functional helps the solution to escape suboptimal local minima in the energy space and give better tracking result. Experimental results show that the proposed method efficiently adapts to the highly deformable lip boundaries even for lips with indistinct edges and colored (adorned) lips where gradient magnitude based or local region based tracking methods respectively fail. We have done a number of experiments to evaluate the performance of our method in comparison with the existing state-of-the-art methods.
{"title":"Lip tracking under varying expressions utilizing domain knowledge","authors":"Swapna Agarwal, D. Mukherjee","doi":"10.1109/NCVPRIPG.2013.6776201","DOIUrl":"https://doi.org/10.1109/NCVPRIPG.2013.6776201","url":null,"abstract":"In recent years the need of a robust facial component tracking especially lip tracking algorithm has increased dramatically. We implement an active contour (snake) model inspired by human perception for lip tracking. In addition to the conventional energy terms for tension, rigidity (internal energy) and gradient magnitude (external energy) we propose to include energy terms from domain knowledge for lip shape constraint and local region profile constraint. Generalized deterministic annealing (GDA) update of the energy functional helps the solution to escape suboptimal local minima in the energy space and give better tracking result. Experimental results show that the proposed method efficiently adapts to the highly deformable lip boundaries even for lips with indistinct edges and colored (adorned) lips where gradient magnitude based or local region based tracking methods respectively fail. We have done a number of experiments to evaluate the performance of our method in comparison with the existing state-of-the-art methods.","PeriodicalId":436402,"journal":{"name":"2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117196440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/NCVPRIPG.2013.6776190
Abhranil Chatterjee, Bijoy Sarkar, Prateeksha Chandraghatgi, K. Seal, Girish Ananthakrishnan
In this paper, we present a search powered approach we have used in building a Video Recommendations Engine for Yahoo hosted videos and Yahoo Video Search. The aim is to increase user engagement by recommending related videos and hence increase revenue by being able to show more advertisements as the user keeps consuming more videos. This system accepts an input context which provides information about the user and the video consumed and returns a set of related videos as recommended. We look at this problem as a multi-faceted problem since the intent of the user at a particular point in time cannot be known deterministically. So we generate the candidate set of recommendations using an ensemble of algorithms and available search signals. We discuss these algorithms and mechanisms for retrieving related videos in details along with an explore-exploit strategy to learn a near optimal ranking of the candidate recommendations, and provide the performance results. This system has been able to increase the number of video plays at Yahoo by 66%.
{"title":"Search based Video Recommendations","authors":"Abhranil Chatterjee, Bijoy Sarkar, Prateeksha Chandraghatgi, K. Seal, Girish Ananthakrishnan","doi":"10.1109/NCVPRIPG.2013.6776190","DOIUrl":"https://doi.org/10.1109/NCVPRIPG.2013.6776190","url":null,"abstract":"In this paper, we present a search powered approach we have used in building a Video Recommendations Engine for Yahoo hosted videos and Yahoo Video Search. The aim is to increase user engagement by recommending related videos and hence increase revenue by being able to show more advertisements as the user keeps consuming more videos. This system accepts an input context which provides information about the user and the video consumed and returns a set of related videos as recommended. We look at this problem as a multi-faceted problem since the intent of the user at a particular point in time cannot be known deterministically. So we generate the candidate set of recommendations using an ensemble of algorithms and available search signals. We discuss these algorithms and mechanisms for retrieving related videos in details along with an explore-exploit strategy to learn a near optimal ranking of the candidate recommendations, and provide the performance results. This system has been able to increase the number of video plays at Yahoo by 66%.","PeriodicalId":436402,"journal":{"name":"2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124768085","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/NCVPRIPG.2013.6776224
J. Banerjee, R. Ray, S. R. K. Vadali, R. Layek, S. N. Shome
In this paper, a shape recognition method is proposed for a few common geometrical shapes including straight line, circle, ellipse, triangle, quadrilateral, pentagon and hexagon. In the present work, two indices namely Unique Shape Signature (USS) and Condensibility (C) are employed for shape recognition of an object. Using the USS index, all the above mentioned non-circular shapes are neatly recognized, whereas, the C index recognized the circular objects. An added advantage of the proposed method is that it can further differentiate triangles, quadrilaterals and both symmetric and non-symmetric shapes of pentagon and hexagon using distance variance (V ar(dsi)) parameter calculated from USS. Applying the proposed method on above mentioned shapes, an overall recognition rate of 98.80% is achieved on several simulated and real objects of different shapes. Proposed method has also been compared with two existing methods, presents better result. Performance of the proposed method is illustrated by applying it on underwater images and it is observed to perform satisfactory on all the images under test.
{"title":"Shape recognition based on shape-signature identification and condensibility: Application to underwater imagery","authors":"J. Banerjee, R. Ray, S. R. K. Vadali, R. Layek, S. N. Shome","doi":"10.1109/NCVPRIPG.2013.6776224","DOIUrl":"https://doi.org/10.1109/NCVPRIPG.2013.6776224","url":null,"abstract":"In this paper, a shape recognition method is proposed for a few common geometrical shapes including straight line, circle, ellipse, triangle, quadrilateral, pentagon and hexagon. In the present work, two indices namely Unique Shape Signature (USS) and Condensibility (C) are employed for shape recognition of an object. Using the USS index, all the above mentioned non-circular shapes are neatly recognized, whereas, the C index recognized the circular objects. An added advantage of the proposed method is that it can further differentiate triangles, quadrilaterals and both symmetric and non-symmetric shapes of pentagon and hexagon using distance variance (V ar(dsi)) parameter calculated from USS. Applying the proposed method on above mentioned shapes, an overall recognition rate of 98.80% is achieved on several simulated and real objects of different shapes. Proposed method has also been compared with two existing methods, presents better result. Performance of the proposed method is illustrated by applying it on underwater images and it is observed to perform satisfactory on all the images under test.","PeriodicalId":436402,"journal":{"name":"2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129773964","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/NCVPRIPG.2013.6776153
Siddharth Srivatsa, Prajwal Shanthakumar, K. Manikantan, S. Ramachandran
The statistical description of the face varies drastically with changes in pose, illumination and expression. These variations make face recognition (FR) even more challenging. In this paper, two novel techniques are proposed, viz., Dual Objective Feature Selection to learn and select only discriminant features and Scaled Euclidean Classification to exploit within-class information for smarter matching. The 1-D discrete cosine transform (DCT) is used for efficient feature extraction. A complete FR system for enhanced recognition performance is presented. Experimental results on three benchmark face databases, namely, Color FERET, CMU PIE and ORL, illustrate the promising performance of the proposed techniques for face recognition.
{"title":"Dual Objective Feature Selection and Scaled Euclidean Classification for face recognition","authors":"Siddharth Srivatsa, Prajwal Shanthakumar, K. Manikantan, S. Ramachandran","doi":"10.1109/NCVPRIPG.2013.6776153","DOIUrl":"https://doi.org/10.1109/NCVPRIPG.2013.6776153","url":null,"abstract":"The statistical description of the face varies drastically with changes in pose, illumination and expression. These variations make face recognition (FR) even more challenging. In this paper, two novel techniques are proposed, viz., Dual Objective Feature Selection to learn and select only discriminant features and Scaled Euclidean Classification to exploit within-class information for smarter matching. The 1-D discrete cosine transform (DCT) is used for efficient feature extraction. A complete FR system for enhanced recognition performance is presented. Experimental results on three benchmark face databases, namely, Color FERET, CMU PIE and ORL, illustrate the promising performance of the proposed techniques for face recognition.","PeriodicalId":436402,"journal":{"name":"2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126919338","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/NCVPRIPG.2013.6776158
Soumyajit Gupta, Rahul Agrawal, R. Layek, J. Mukhopadhyay
Visual attention is an indispensable component of complex vision tasks. When looking at a complex scene, our ocular perception is confronted with a large amount of data that needs to be broken down for processing by our psychovisual system. Selective visual attention provides a mechanism for serializing the visual data, allowing for sequential processing of the content of the scene. A Bottom-Up computational model is described that simulates the psycho-visual model of saliency based on features of intensity and color. The method gives sequential priorities to objects which other computational models cannot account for. The results demonstrate a fast execution time, full resolution maps and high detection accuracy. The model is applicable on both natural and artificial images.
{"title":"Psychovisual saliency in color images","authors":"Soumyajit Gupta, Rahul Agrawal, R. Layek, J. Mukhopadhyay","doi":"10.1109/NCVPRIPG.2013.6776158","DOIUrl":"https://doi.org/10.1109/NCVPRIPG.2013.6776158","url":null,"abstract":"Visual attention is an indispensable component of complex vision tasks. When looking at a complex scene, our ocular perception is confronted with a large amount of data that needs to be broken down for processing by our psychovisual system. Selective visual attention provides a mechanism for serializing the visual data, allowing for sequential processing of the content of the scene. A Bottom-Up computational model is described that simulates the psycho-visual model of saliency based on features of intensity and color. The method gives sequential priorities to objects which other computational models cannot account for. The results demonstrate a fast execution time, full resolution maps and high detection accuracy. The model is applicable on both natural and artificial images.","PeriodicalId":436402,"journal":{"name":"2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123289979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/NCVPRIPG.2013.6776154
Sai Hareesh Anamandra, V. Chandrasekaran
Designing a robust image local descriptor for the purpose of pattern recognition and classification has been an active area of research. Towards this end, a number of local descriptors based on Weber's law have been proposed recently. Notable among them are Weber Local Descriptor (WLD), Weber Local Binary Pattern (WLBP) and Gabor Weber Local Descriptor (GWLD). Experiments reveal their inability to classify patterns under noisy environments. Our analysis indicates that the components of the WLD: differential excitation and orientation are to be redesigned for robustness and computational efficiency.
{"title":"CHILD: A robust Computationally-Efficient Histogram-based Image Local Descriptor","authors":"Sai Hareesh Anamandra, V. Chandrasekaran","doi":"10.1109/NCVPRIPG.2013.6776154","DOIUrl":"https://doi.org/10.1109/NCVPRIPG.2013.6776154","url":null,"abstract":"Designing a robust image local descriptor for the purpose of pattern recognition and classification has been an active area of research. Towards this end, a number of local descriptors based on Weber's law have been proposed recently. Notable among them are Weber Local Descriptor (WLD), Weber Local Binary Pattern (WLBP) and Gabor Weber Local Descriptor (GWLD). Experiments reveal their inability to classify patterns under noisy environments. Our analysis indicates that the components of the WLD: differential excitation and orientation are to be redesigned for robustness and computational efficiency.","PeriodicalId":436402,"journal":{"name":"2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126365149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/NCVPRIPG.2013.6776193
Somnath Dutta, Sumandeep Banerjee, P. Biswas, Partha Bhowmick
We present an improved mesh denoising method based on 3D geometric bilateral filtering. Its novelty is that it can preserve the details of the object as well as reduce the noise in an effective manner. The previous approach of geometric bilateral filtering for 3D-scan points has a limitation that it reduces the point density, thereby losing the details present in the object. The approach proposed by us, on the contrary, works on the surface mesh obtained after triangulating the 3D-scan points without any data downsampling. Each vertex of the mesh is repositioned appropriately based on the estimated centroid of the vertices in its local neighborhood and a Gaussian weight function. Experimental results demonstrate its strength, efficiency, and robustness.
{"title":"Mesh denoising by improved 3D geometric bilateral filter","authors":"Somnath Dutta, Sumandeep Banerjee, P. Biswas, Partha Bhowmick","doi":"10.1109/NCVPRIPG.2013.6776193","DOIUrl":"https://doi.org/10.1109/NCVPRIPG.2013.6776193","url":null,"abstract":"We present an improved mesh denoising method based on 3D geometric bilateral filtering. Its novelty is that it can preserve the details of the object as well as reduce the noise in an effective manner. The previous approach of geometric bilateral filtering for 3D-scan points has a limitation that it reduces the point density, thereby losing the details present in the object. The approach proposed by us, on the contrary, works on the surface mesh obtained after triangulating the 3D-scan points without any data downsampling. Each vertex of the mesh is repositioned appropriately based on the estimated centroid of the vertices in its local neighborhood and a Gaussian weight function. Experimental results demonstrate its strength, efficiency, and robustness.","PeriodicalId":436402,"journal":{"name":"2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)","volume":"34 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116592442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/NCVPRIPG.2013.6776188
R. Raja, S. Roomi, D. Dharmalakshmi
Scene classification using semantic description has gained much attention towards automatic image retrieval. In many cases, visual appearance of images get affected by environmental conditions such as low lighting and viewing conditions. Such problems in semantic scenes pose difficult challenges during the classification of sceneries. To address this issue, a new outdoor scene classification method for using low level feature has been proposed in this work. To support automatic scene classification at the concept level an efficient illumination and rotation invariant low level features such as color, texture and edge like features have been used in conjunction with multiclass Support Vector Machine (SVM). In this work, we have taken scene categories like mountains, forests, highways, rivers, buildings etc., from the outdoor scenes for classification experimentation. From the experimental results, we demonstrate that the proposed method provides better classification in the large scale image databases like Eight scene category, upright scene and COREL dataset and gives better performance in terms of classification accuracy.
{"title":"Outdoor scene classification using invariant features","authors":"R. Raja, S. Roomi, D. Dharmalakshmi","doi":"10.1109/NCVPRIPG.2013.6776188","DOIUrl":"https://doi.org/10.1109/NCVPRIPG.2013.6776188","url":null,"abstract":"Scene classification using semantic description has gained much attention towards automatic image retrieval. In many cases, visual appearance of images get affected by environmental conditions such as low lighting and viewing conditions. Such problems in semantic scenes pose difficult challenges during the classification of sceneries. To address this issue, a new outdoor scene classification method for using low level feature has been proposed in this work. To support automatic scene classification at the concept level an efficient illumination and rotation invariant low level features such as color, texture and edge like features have been used in conjunction with multiclass Support Vector Machine (SVM). In this work, we have taken scene categories like mountains, forests, highways, rivers, buildings etc., from the outdoor scenes for classification experimentation. From the experimental results, we demonstrate that the proposed method provides better classification in the large scale image databases like Eight scene category, upright scene and COREL dataset and gives better performance in terms of classification accuracy.","PeriodicalId":436402,"journal":{"name":"2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121468437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：