This paper presents a new approach for efficient object detection and matching in images and videos. We propose a stage based on a classification scheme that classifies the extracted features in new images into object features and non-object features. This binary classification scheme has turned out to be an efficient tool that can be used for object detection and matching. By means of this classification not only the matching process becomes more robust and faster but also the robust object registration becomes fast. We provide quantitative evaluations showing the advantages of using the classification stage for object matching and registration. Our approach could lend itself nicely to real-time object tracking and detection.
{"title":"Efficient Object Detection and Matching Using Feature Classification","authors":"F. Dornaika, Fadi Chakik","doi":"10.1109/ICPR.2010.753","DOIUrl":"https://doi.org/10.1109/ICPR.2010.753","url":null,"abstract":"This paper presents a new approach for efficient object detection and matching in images and videos. We propose a stage based on a classification scheme that classifies the extracted features in new images into object features and non-object features. This binary classification scheme has turned out to be an efficient tool that can be used for object detection and matching. By means of this classification not only the matching process becomes more robust and faster but also the robust object registration becomes fast. We provide quantitative evaluations showing the advantages of using the classification stage for object matching and registration. Our approach could lend itself nicely to real-time object tracking and detection.","PeriodicalId":309591,"journal":{"name":"2010 20th International Conference on Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128062375","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}
When computing optical flow with region-based matching, very few of them can be reliably obtained, especially for the high-contrast areas or those with little texture. Instead of using a single pixel from the reference frame, non-deterministic motion utilizes multiple pixels within a neighborhood to represent the corresponding pixel in the current frame. Although remarkable improvement has been made with this method, the weight associated to each reference pixel is quite sensitive to the selection of its standard deviation. To address this issue, a dual probability is presented in this paper. Intuitively, it enhances those weights of pixels that are more similar to its counterpart in the current frame, while suppressing the rest of them. Experimental results show that the proposed method is effective to deal with intense motion and occlusion, especially in the case of reducing the adverse impact of noise.
{"title":"A Comprehensive Evaluation on Non-deterministic Motion Estimation","authors":"Changzhu Wu, Qing Wang","doi":"10.1109/ICPR.2010.571","DOIUrl":"https://doi.org/10.1109/ICPR.2010.571","url":null,"abstract":"When computing optical flow with region-based matching, very few of them can be reliably obtained, especially for the high-contrast areas or those with little texture. Instead of using a single pixel from the reference frame, non-deterministic motion utilizes multiple pixels within a neighborhood to represent the corresponding pixel in the current frame. Although remarkable improvement has been made with this method, the weight associated to each reference pixel is quite sensitive to the selection of its standard deviation. To address this issue, a dual probability is presented in this paper. Intuitively, it enhances those weights of pixels that are more similar to its counterpart in the current frame, while suppressing the rest of them. Experimental results show that the proposed method is effective to deal with intense motion and occlusion, especially in the case of reducing the adverse impact of noise.","PeriodicalId":309591,"journal":{"name":"2010 20th International Conference on Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114048596","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}
In this paper we survey two multi-dimensional Scale Saliency approaches based on graphs and the k-d partition algorithm. In the latter case we introduce a new divergence metric and we show experimentally its suitability. We also show an application of multi-dimensional Scale Saliency to texture discrimination. We demonstrate that the use of multi-dimensional data can improve the performance of texture retrieval based on feature extraction.
{"title":"Entropy Estimation and Multi-Dimensional Scale Saliency","authors":"P. Suau, Francisco Escolano","doi":"10.1109/ICPR.2010.171","DOIUrl":"https://doi.org/10.1109/ICPR.2010.171","url":null,"abstract":"In this paper we survey two multi-dimensional Scale Saliency approaches based on graphs and the k-d partition algorithm. In the latter case we introduce a new divergence metric and we show experimentally its suitability. We also show an application of multi-dimensional Scale Saliency to texture discrimination. We demonstrate that the use of multi-dimensional data can improve the performance of texture retrieval based on feature extraction.","PeriodicalId":309591,"journal":{"name":"2010 20th International Conference on Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125108935","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}
In this paper, we propose an active contour with threshold value to detect objects and at the same time get rid of unimportant parts rather than extract all information. The basic ideal of our model is to introduce a weight matrix into region-based active contours, which can enhance the weight for the main parts while filter the weak intensity, such as shadows, illumination and so on. Moreover, we can choose threshold value to set weight matrix manually for accurate image segmentation. Thus, the proposed method can extract objects of interest in practice. Coupled partial differential equations are used to implement this method with level set algorithms. Experimental results show the advantages of our method in terms of accuracy for image segmentation.
{"title":"Active Contours with Thresholding Value for Image Segmentation","authors":"Gang Chen, Haiying Zhang, I-Ping Chen, Wen Yang","doi":"10.1109/ICPR.2010.555","DOIUrl":"https://doi.org/10.1109/ICPR.2010.555","url":null,"abstract":"In this paper, we propose an active contour with threshold value to detect objects and at the same time get rid of unimportant parts rather than extract all information. The basic ideal of our model is to introduce a weight matrix into region-based active contours, which can enhance the weight for the main parts while filter the weak intensity, such as shadows, illumination and so on. Moreover, we can choose threshold value to set weight matrix manually for accurate image segmentation. Thus, the proposed method can extract objects of interest in practice. Coupled partial differential equations are used to implement this method with level set algorithms. Experimental results show the advantages of our method in terms of accuracy for image segmentation.","PeriodicalId":309591,"journal":{"name":"2010 20th International Conference on Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126348132","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}
Ghosting artifact in the field of image stitching is a common problem and the elimination of it is not an easy task. In this paper, we propose an intuitive technique according to a stitching line based on a novel energy map which is essentially a combination of gradient map which indicates the presence of structures and prominence map which determines the attractiveness of a region. We consider a region is of significance only if it is both structural and attractive. Using this improved energy map, the stitching line can easily skirt around the moving objects or salient parts based on the philosophy that human eyes mostly notice only the salient features of an image. We compare result of our method to those of 4 state-of-the-art image stitching methods and it turns out that our method outperforms the 4 methods in removing ghosting artifacts.
{"title":"De-ghosting for Image Stitching with Automatic Content-Awareness","authors":"Yu Tang, Jungpil Shin","doi":"10.1109/ICPR.2010.541","DOIUrl":"https://doi.org/10.1109/ICPR.2010.541","url":null,"abstract":"Ghosting artifact in the field of image stitching is a common problem and the elimination of it is not an easy task. In this paper, we propose an intuitive technique according to a stitching line based on a novel energy map which is essentially a combination of gradient map which indicates the presence of structures and prominence map which determines the attractiveness of a region. We consider a region is of significance only if it is both structural and attractive. Using this improved energy map, the stitching line can easily skirt around the moving objects or salient parts based on the philosophy that human eyes mostly notice only the salient features of an image. We compare result of our method to those of 4 state-of-the-art image stitching methods and it turns out that our method outperforms the 4 methods in removing ghosting artifacts.","PeriodicalId":309591,"journal":{"name":"2010 20th International Conference on Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131221199","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}
Although Support Vector Machines(SVM) succeed in classifying several image databases using image descriptors proposed in the literature, no single descriptor can be optimal for general object categorization. This paper describes a novel framework to learn the optimal combination of kernels corresponding to multiple image descriptors before SVM training, leading to solve a quadratic programming problem efficiently. Our framework takes into account the variation of kernel matrix and imbalanced dataset, which are common in real world image categorization tasks. Experimental results on Graz-01 and Caltech-101 image databases show the effectiveness and robustness of our algorithm.
{"title":"Learning the Kernel Combination for Object Categorization","authors":"Deyuan Zhang, Xiaolong Wang, Bingquan Liu","doi":"10.1109/ICPR.2010.718","DOIUrl":"https://doi.org/10.1109/ICPR.2010.718","url":null,"abstract":"Although Support Vector Machines(SVM) succeed in classifying several image databases using image descriptors proposed in the literature, no single descriptor can be optimal for general object categorization. This paper describes a novel framework to learn the optimal combination of kernels corresponding to multiple image descriptors before SVM training, leading to solve a quadratic programming problem efficiently. Our framework takes into account the variation of kernel matrix and imbalanced dataset, which are common in real world image categorization tasks. Experimental results on Graz-01 and Caltech-101 image databases show the effectiveness and robustness of our algorithm.","PeriodicalId":309591,"journal":{"name":"2010 20th International Conference on Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125390868","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}
In this paper we propose a new multi-view semi-supervised learning algorithm called Local Co-Training(LCT). The proposed algorithm employs a set of local models with vector outputs to model the relations among examples in a local region on each view, and iteratively refines the dominant local models (i.e. the local models related to the unlabeled examples chosen for enriching the training set) using unlabeled examples by the co-training process. Compared with previous co-training style algorithms, local co-training has two advantages: firstly, it has higher classification precision by introducing local learning; secondly, only the dominant local models need to be updated, which significantly decreases the computational load. Experiments on WebKB and Cora datasets demonstrate that LCT algorithm can effectively exploit unlabeled data to improve the performance of web page classification.
{"title":"Enhancing Web Page Classification via Local Co-training","authors":"Youtian Du, X. Guan, Zhongmin Cai","doi":"10.1109/ICPR.2010.712","DOIUrl":"https://doi.org/10.1109/ICPR.2010.712","url":null,"abstract":"In this paper we propose a new multi-view semi-supervised learning algorithm called Local Co-Training(LCT). The proposed algorithm employs a set of local models with vector outputs to model the relations among examples in a local region on each view, and iteratively refines the dominant local models (i.e. the local models related to the unlabeled examples chosen for enriching the training set) using unlabeled examples by the co-training process. Compared with previous co-training style algorithms, local co-training has two advantages: firstly, it has higher classification precision by introducing local learning; secondly, only the dominant local models need to be updated, which significantly decreases the computational load. Experiments on WebKB and Cora datasets demonstrate that LCT algorithm can effectively exploit unlabeled data to improve the performance of web page classification.","PeriodicalId":309591,"journal":{"name":"2010 20th International Conference on Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127042609","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}
In this paper, we present a monocular camera based terrain classification scheme. The uniqueness of the proposed scheme is that it inherently incorporates spatial smoothness while segmenting a image, without requirement of post-processing smoothing methods. The algorithm is extremely fast because it is build on top of a Random Forest classifier. We present comparison across features and classifiers. The baseline algorithm uses color, texture and their combination with classifiers such as SVM and Random Forests. We further enhance the algorithm through a label transfer method. The efficacy of the proposed solution can be seen as we reach a low error rates on both our dataset and other publicly available datasets.
{"title":"Fast and Spatially-Smooth Terrain Classification Using Monocular Camera","authors":"Chetan Jakkoju, K. Krishna, C. V. Jawahar","doi":"10.1109/ICPR.2010.987","DOIUrl":"https://doi.org/10.1109/ICPR.2010.987","url":null,"abstract":"In this paper, we present a monocular camera based terrain classification scheme. The uniqueness of the proposed scheme is that it inherently incorporates spatial smoothness while segmenting a image, without requirement of post-processing smoothing methods. The algorithm is extremely fast because it is build on top of a Random Forest classifier. We present comparison across features and classifiers. The baseline algorithm uses color, texture and their combination with classifiers such as SVM and Random Forests. We further enhance the algorithm through a label transfer method. The efficacy of the proposed solution can be seen as we reach a low error rates on both our dataset and other publicly available datasets.","PeriodicalId":309591,"journal":{"name":"2010 20th International Conference on Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127892639","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}
In this paper we propose an approach for the problem of single channel source separation of speech and music signals. Our approach is based on representing each source's power spectral density using dictionaries and nonlinearly projecting the mixture signal spectrum onto the combined span of the dictionary entries. We encourage sparsity and continuity of the dictionary coefficients using penalty terms (or log-priors) in an optimization framework. We propose to use a novel coordinate descent technique for optimization, which nicely handles nonnegativity constraints and nonquadratic penalty terms. We use an adaptive Wiener filter, and spectral subtraction to reconstruct both of the sources from the mixture data after corresponding power spectral densities (PSDs) are estimated for each source. Using conventional metrics, we measure the performance of the system on simulated mixtures of single person speech and piano music sources. The results indicate that the proposed method is a promising technique for low speech-to-music ratio conditions and that sparsity and continuity priors help improve the performance of the proposed system.
{"title":"Semi-blind Speech-Music Separation Using Sparsity and Continuity Priors","authors":"Hakan Erdogan, Emad M. Grais","doi":"10.1109/ICPR.2010.1129","DOIUrl":"https://doi.org/10.1109/ICPR.2010.1129","url":null,"abstract":"In this paper we propose an approach for the problem of single channel source separation of speech and music signals. Our approach is based on representing each source's power spectral density using dictionaries and nonlinearly projecting the mixture signal spectrum onto the combined span of the dictionary entries. We encourage sparsity and continuity of the dictionary coefficients using penalty terms (or log-priors) in an optimization framework. We propose to use a novel coordinate descent technique for optimization, which nicely handles nonnegativity constraints and nonquadratic penalty terms. We use an adaptive Wiener filter, and spectral subtraction to reconstruct both of the sources from the mixture data after corresponding power spectral densities (PSDs) are estimated for each source. Using conventional metrics, we measure the performance of the system on simulated mixtures of single person speech and piano music sources. The results indicate that the proposed method is a promising technique for low speech-to-music ratio conditions and that sparsity and continuity priors help improve the performance of the proposed system.","PeriodicalId":309591,"journal":{"name":"2010 20th International Conference on Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128269726","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}
The state-of-the-art methods for speaker verification are based on the support vector machine. The Gaussian supervector SVM is a typical method which uses the Gaussian mixture model for creating “feature vectors” for the discriminative SVM. And all GMMs are adapted from the same universal background model, which is got by maximum likelihood estimation on a large number of data sets. So the UBM should cover the feature space widely as possible. We propose a new method to estimate the parameters of the UBM by combining the likelihood and the Kullback-Leibler distances in the UBM. Its aim is to find the model parameters which get the high likelihood value and all Gaussian distributions are dispersed to cover the feature space in a great measuring. Experiments on NIST 2001 task show that our method can improve the performance obviously.
{"title":"Combining the Likelihood and the Kullback-Leibler Distance in Estimating the Universal Background Model for Speaker Verification Using SVM","authors":"Zhenchun Lei","doi":"10.1109/ICPR.2010.1106","DOIUrl":"https://doi.org/10.1109/ICPR.2010.1106","url":null,"abstract":"The state-of-the-art methods for speaker verification are based on the support vector machine. The Gaussian supervector SVM is a typical method which uses the Gaussian mixture model for creating “feature vectors” for the discriminative SVM. And all GMMs are adapted from the same universal background model, which is got by maximum likelihood estimation on a large number of data sets. So the UBM should cover the feature space widely as possible. We propose a new method to estimate the parameters of the UBM by combining the likelihood and the Kullback-Leibler distances in the UBM. Its aim is to find the model parameters which get the high likelihood value and all Gaussian distributions are dispersed to cover the feature space in a great measuring. Experiments on NIST 2001 task show that our method can improve the performance obviously.","PeriodicalId":309591,"journal":{"name":"2010 20th International Conference on Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128403132","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：