This paper addresses the problem of interactive image segmentation with a user-supplied object bounding box. The underlying problem is the classification of pixels into foreground and background, where only background information is provided with sample pixels. Many approaches treat appearance models as an unknown variable and optimize the segmentation and appearance alternatively, in an expectation maximization manner. In this paper, we describe a novel approach to this problem: the objective function is expressed purely in terms of the unknown segmentation and can be optimized using only one minimum cut calculation. We aim to optimize the trade-off of making the foreground layer as large as possible while keeping the similarity between the foreground and background layers as small as possible. This similarity is formulated using the similarities of distant pixel pairs. We evaluated our algorithm on the GrabCut dataset and demonstrated that high-quality segmentations were attained at a fast calculation speed.
{"title":"Bounding-Box Based Segmentation with Single Min-cut Using Distant Pixel Similarity","authors":"V. Pham, Keita Takahashi, T. Naemura","doi":"10.1109/ICPR.2010.1074","DOIUrl":"https://doi.org/10.1109/ICPR.2010.1074","url":null,"abstract":"This paper addresses the problem of interactive image segmentation with a user-supplied object bounding box. The underlying problem is the classification of pixels into foreground and background, where only background information is provided with sample pixels. Many approaches treat appearance models as an unknown variable and optimize the segmentation and appearance alternatively, in an expectation maximization manner. In this paper, we describe a novel approach to this problem: the objective function is expressed purely in terms of the unknown segmentation and can be optimized using only one minimum cut calculation. We aim to optimize the trade-off of making the foreground layer as large as possible while keeping the similarity between the foreground and background layers as small as possible. This similarity is formulated using the similarities of distant pixel pairs. We evaluated our algorithm on the GrabCut dataset and demonstrated that high-quality segmentations were attained at a fast calculation speed.","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":"129501070","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}
A new algorithm for performing classification with imperfectly labeled data is presented. The proposed approach is motivated by the insight that the average prediction of a group of sufficiently informed people is often more accurate than the prediction of any one supposed expert. This idea that the "wisdom of crowds" can outperform a single expert is implemented by drawing sets of labels as samples from a Bernoulli distribution with a specified labeling error rate. Additionally, ideas from multiple imputation are exploited to provide a principled way for determining an appropriate number of label sampling rounds to consider. The approach is demonstrated in the context of an underwater mine classification application on real synthetic aperture sonar data collected at sea, with promising results.
{"title":"Underwater Mine Classification with Imperfect Labels","authors":"David P. Williams","doi":"10.1109/ICPR.2010.1011","DOIUrl":"https://doi.org/10.1109/ICPR.2010.1011","url":null,"abstract":"A new algorithm for performing classification with imperfectly labeled data is presented. The proposed approach is motivated by the insight that the average prediction of a group of sufficiently informed people is often more accurate than the prediction of any one supposed expert. This idea that the \"wisdom of crowds\" can outperform a single expert is implemented by drawing sets of labels as samples from a Bernoulli distribution with a specified labeling error rate. Additionally, ideas from multiple imputation are exploited to provide a principled way for determining an appropriate number of label sampling rounds to consider. The approach is demonstrated in the context of an underwater mine classification application on real synthetic aperture sonar data collected at sea, with promising results.","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":"115016755","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}
This paper describes a stereo-based person tracking method for a person following robot. Many previous works on person tracking use laser range finders which can provide very accurate range measurements. Stereo-based systems have also been popular, but most of them are not used for controlling a real robot. We previously developed a tracking method which uses depth templates of person shape applied to a dense depth image. The method, however, sometimes failed when complex occlusions occurred. In this paper, we propose an accurate, stable tracking method using overlapping silhouette templates which consider how persons overlap in the image. Experimental results show the effectiveness of the proposed method.
{"title":"Stereo-Based Multi-person Tracking Using Overlapping Silhouette Templates","authors":"Junji Satake, J. Miura","doi":"10.1109/ICPR.2010.1046","DOIUrl":"https://doi.org/10.1109/ICPR.2010.1046","url":null,"abstract":"This paper describes a stereo-based person tracking method for a person following robot. Many previous works on person tracking use laser range finders which can provide very accurate range measurements. Stereo-based systems have also been popular, but most of them are not used for controlling a real robot. We previously developed a tracking method which uses depth templates of person shape applied to a dense depth image. The method, however, sometimes failed when complex occlusions occurred. In this paper, we propose an accurate, stable tracking method using overlapping silhouette templates which consider how persons overlap in the image. Experimental results show the effectiveness of the proposed method.","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":"123653598","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}
Jingyong Su, Zhiqiang Zhu, Anuj Srivastava, F. Huffer
We present a novel statistical framework for detecting pre-determined shape classes in 2D cluttered point clouds, which are in turn extracted from images. In this model based approach, we use a 1D Poisson process for sampling points on shapes, a 2D Poisson process for points from background clutter, and an additive Gaussian model for noise. Combining these with a past stochastic model on shapes of continuous 2D contours, and optimization over unknown pose and scale, we develop a generalized likelihood ratio test for shape detection. We demonstrate the efficiency of this method and its robustness to clutter using both simulated and real data.
{"title":"Detection of Shapes in 2D Point Clouds Generated from Images","authors":"Jingyong Su, Zhiqiang Zhu, Anuj Srivastava, F. Huffer","doi":"10.1109/ICPR.2010.647","DOIUrl":"https://doi.org/10.1109/ICPR.2010.647","url":null,"abstract":"We present a novel statistical framework for detecting pre-determined shape classes in 2D cluttered point clouds, which are in turn extracted from images. In this model based approach, we use a 1D Poisson process for sampling points on shapes, a 2D Poisson process for points from background clutter, and an additive Gaussian model for noise. Combining these with a past stochastic model on shapes of continuous 2D contours, and optimization over unknown pose and scale, we develop a generalized likelihood ratio test for shape detection. We demonstrate the efficiency of this method and its robustness to clutter using both simulated and real data.","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":"129129580","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 introduce a new sharpening method which guarantees colour constancy and resolves the problem of equiluminance colours. The algorithm is similar to unsharp masking in that the gradients are calculated at different scales by blurring the original with a variable size kernel. The main difference is in the blurring stage where we calculate the average of an n times n neighborhood by projecting each colour vector onto the space of the center pixel before averaging. Thus starting with the center pixel we define a projection matrix onto the space of that vector. Each neighboring colour is then projected onto the center and the result is summed up. The projection step results in an average vector which shares the direction of the original center pixel. The difference between the center pixel and the average is by definition a vector which is scalar away from the center pixel. Thus adding the average to the center pixel is guaranteed not to result in colour shifts. This projection step is also shown to remedy the problem of equiluminance colours and can be used for $m$-dimensional data. Finally, the results indicate that the new sharpening method results in better sharpening than that achieved using unsharp masking with noticeably less halos around strong edges. The latter aspect of the algorithm is believed to be due to the asymmetric nature of the projection step.
{"title":"Colour Constant Image Sharpening","authors":"A. Alsam","doi":"10.1109/ICPR.2010.1104","DOIUrl":"https://doi.org/10.1109/ICPR.2010.1104","url":null,"abstract":"In this paper, we introduce a new sharpening method which guarantees colour constancy and resolves the problem of equiluminance colours. The algorithm is similar to unsharp masking in that the gradients are calculated at different scales by blurring the original with a variable size kernel. The main difference is in the blurring stage where we calculate the average of an n times n neighborhood by projecting each colour vector onto the space of the center pixel before averaging. Thus starting with the center pixel we define a projection matrix onto the space of that vector. Each neighboring colour is then projected onto the center and the result is summed up. The projection step results in an average vector which shares the direction of the original center pixel. The difference between the center pixel and the average is by definition a vector which is scalar away from the center pixel. Thus adding the average to the center pixel is guaranteed not to result in colour shifts. This projection step is also shown to remedy the problem of equiluminance colours and can be used for $m$-dimensional data. Finally, the results indicate that the new sharpening method results in better sharpening than that achieved using unsharp masking with noticeably less halos around strong edges. The latter aspect of the algorithm is believed to be due to the asymmetric nature of the projection step.","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":"125944653","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}
Ryoichi Yamakoshi, Kousuke Hirasawa, H. Okuda, H. Kage, K. Sumi, H. Sakamoto, Yuri Ivanov, Toshihiro Yanou, D. Suga, Masao Murakami
In this paper we present a robust alignment algorithm for correcting the effects of out-of-plane rotation to be used for automatic alignment of the Computed Tomography (CT) volumes and the generally low quality fluoroscopic images for radiotherapy applications. Analyzing not only in-plane but also out-of-plane rotation effects on the Dignitary Reconstructed Radiograph (DRR) images, we develop simple alignment algorithm that extracts a set of implicit features from DRR. Using these SIFT-based features, we align DRRs with the fluoroscopic images of the patient and evaluate the alignment accuracy. We compare our approach with traditional techniques based on gradient-based operators and show that our algorithm performs faster while in most cases delivering higher accuracy.
{"title":"Implicit Feature-Based Alignment System for Radiotherapy","authors":"Ryoichi Yamakoshi, Kousuke Hirasawa, H. Okuda, H. Kage, K. Sumi, H. Sakamoto, Yuri Ivanov, Toshihiro Yanou, D. Suga, Masao Murakami","doi":"10.1109/ICPR.2010.559","DOIUrl":"https://doi.org/10.1109/ICPR.2010.559","url":null,"abstract":"In this paper we present a robust alignment algorithm for correcting the effects of out-of-plane rotation to be used for automatic alignment of the Computed Tomography (CT) volumes and the generally low quality fluoroscopic images for radiotherapy applications. Analyzing not only in-plane but also out-of-plane rotation effects on the Dignitary Reconstructed Radiograph (DRR) images, we develop simple alignment algorithm that extracts a set of implicit features from DRR. Using these SIFT-based features, we align DRRs with the fluoroscopic images of the patient and evaluate the alignment accuracy. We compare our approach with traditional techniques based on gradient-based operators and show that our algorithm performs faster while in most cases delivering higher accuracy.","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":"130394398","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}
We present a method of performing kernel space domain description of a dataset with incomplete entries without the need for imputation, allowing kernel features of a class of data with missing features to be rigorously described. This addresses the problem that absent data completion is usually required before kernel classifiers, such as support vector domain description (SVDD), can be applied; equally, few existing techniques for incomplete data adequately address the issue of kernel spaces. Our method, which we call instance-specific domain description (ISDD), uses a parametrisation framework to compute minimal kernelised distances between data points with missing features through a series of optimisation runs, allowing evaluation of the kernel distance while avoiding subjective completions of missing data. We compare results of our method against those achieved by SVDD applied to an imputed dataset, using synthetic and experimental datasets where feature absence has a non-trivial structure. We show that our methods can achieve tighter sphere bounds when applied to linear and quadratic kernels.
{"title":"Kernel Domain Description with Incomplete Data: Using Instance-Specific Margins to Avoid Imputation","authors":"Adam Gripton, W. Lu","doi":"10.1109/ICPR.2010.716","DOIUrl":"https://doi.org/10.1109/ICPR.2010.716","url":null,"abstract":"We present a method of performing kernel space domain description of a dataset with incomplete entries without the need for imputation, allowing kernel features of a class of data with missing features to be rigorously described. This addresses the problem that absent data completion is usually required before kernel classifiers, such as support vector domain description (SVDD), can be applied; equally, few existing techniques for incomplete data adequately address the issue of kernel spaces. Our method, which we call instance-specific domain description (ISDD), uses a parametrisation framework to compute minimal kernelised distances between data points with missing features through a series of optimisation runs, allowing evaluation of the kernel distance while avoiding subjective completions of missing data. We compare results of our method against those achieved by SVDD applied to an imputed dataset, using synthetic and experimental datasets where feature absence has a non-trivial structure. We show that our methods can achieve tighter sphere bounds when applied to linear and quadratic kernels.","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":"132186748","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 work on automated scribe identification on a new Middle-English manuscript dataset from around the 14th -- 15th century. We discuss the image and textual problems encountered in processing historical documents, and demonstrate the effect of accounting for manuscript style on the writer identification rate. The grapheme codebook method is used to achieve a Top-1 classification accuracy of up to 77% with a modification to the distance measure. The performance of the Sparse Multinomial Logistic Regression classifier is compared against five k-nn classifiers. We also consider classification against the principal components and propose a method for visualising the principal component vectors in terms of the original grapheme features.
{"title":"Scribe Identification in Medieval English Manuscripts","authors":"Tara Gilliam, Richard C. Wilson, J. A. Clark","doi":"10.1109/ICPR.2010.463","DOIUrl":"https://doi.org/10.1109/ICPR.2010.463","url":null,"abstract":"In this paper we present work on automated scribe identification on a new Middle-English manuscript dataset from around the 14th -- 15th century. We discuss the image and textual problems encountered in processing historical documents, and demonstrate the effect of accounting for manuscript style on the writer identification rate. The grapheme codebook method is used to achieve a Top-1 classification accuracy of up to 77% with a modification to the distance measure. The performance of the Sparse Multinomial Logistic Regression classifier is compared against five k-nn classifiers. We also consider classification against the principal components and propose a method for visualising the principal component vectors in terms of the original grapheme features.","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":"115163694","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}
Automatically tracking human body parts is a difficult problem because of background clutters, missing body parts, and the high degrees of freedoms and complex kinematics of the articulated human body. This paper presents the sequential Markov random fields (SMRFs) for tracking and labeling moving human body parts automatically by learning the spatio-temporal structures of human motions in the setting of occlusions and clutters. We employ a hybrid strategy, where the temporal dependencies between two successive human poses are described by the sequential Monte Carlo method, and the spatial relationships between body parts in a pose is described by the Markov random fields. Efficient inference and learning algorithms are developed based on the relaxation labeling. Experimental results show that the SMRF can effectively track human body parts in natural scenes.
{"title":"Human Body Parts Tracking Using Sequential Markov Random Fields","authors":"Xiao-Qin Cao, Jia Zeng, Zhi-Qiang Liu","doi":"10.1109/ICPR.2010.1158","DOIUrl":"https://doi.org/10.1109/ICPR.2010.1158","url":null,"abstract":"Automatically tracking human body parts is a difficult problem because of background clutters, missing body parts, and the high degrees of freedoms and complex kinematics of the articulated human body. This paper presents the sequential Markov random fields (SMRFs) for tracking and labeling moving human body parts automatically by learning the spatio-temporal structures of human motions in the setting of occlusions and clutters. We employ a hybrid strategy, where the temporal dependencies between two successive human poses are described by the sequential Monte Carlo method, and the spatial relationships between body parts in a pose is described by the Markov random fields. Efficient inference and learning algorithms are developed based on the relaxation labeling. Experimental results show that the SMRF can effectively track human body parts in natural scenes.","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":"117173316","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}
Probabilistic latent semantic analysis is enhanced with long distance bigram models in order to improve word clustering. The long distance bigram probabilities and the interpolated long distance bigram probabilities at varying distances within a context capture different aspects of contextual information. In addition, the baseline bigram, which incorporates trigger-pairs for various histories, is tested in the same framework. The experimental results collected on publicly available corpora (CISI, Cran field, Medline, and NPL) demonstrate the superiority of the long distance bigrams over the baseline bigrams as well as the superiority of the interpolated long distance bigrams against the long distance bigrams and the baseline bigram with trigger-pairs in yielding more compact clusters containing less outliers.
{"title":"Word Clustering Using PLSA Enhanced with Long Distance Bigrams","authors":"Bassiou Nikoletta, Kotropoulos Constantine","doi":"10.1109/ICPR.2010.1027","DOIUrl":"https://doi.org/10.1109/ICPR.2010.1027","url":null,"abstract":"Probabilistic latent semantic analysis is enhanced with long distance bigram models in order to improve word clustering. The long distance bigram probabilities and the interpolated long distance bigram probabilities at varying distances within a context capture different aspects of contextual information. In addition, the baseline bigram, which incorporates trigger-pairs for various histories, is tested in the same framework. The experimental results collected on publicly available corpora (CISI, Cran field, Medline, and NPL) demonstrate the superiority of the long distance bigrams over the baseline bigrams as well as the superiority of the interpolated long distance bigrams against the long distance bigrams and the baseline bigram with trigger-pairs in yielding more compact clusters containing less outliers.","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":"121670661","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：