The Brain Extraction Tool (BET) developed by Smith is widely used for brain segmentation due to its simplicity, accuracy and insensitivity to parameter settings. However, it typically requires a large number of iterations to generate acceptable results. It also sometimes fails to recognize boundaries of the brain. Moreover, obvious under-segmentation occurs for some datasets. In this paper, we present an improved BET method where at each iteration, we enhance the vertex displacement, add a new search path and embed an independent surface reconstruction process. These strategies lead to much faster convergence. Furthermore, a scheme based on fuzzy c-means is proposed to refine the segmentation. Experimental results based on various datsets demonstrated that the proposed method significantly outperforms the original BET and other competing methods.
{"title":"An Improved BET Method for Brain Segmentation","authors":"Liping Wang, Ziming Zeng, R. Zwiggelaar","doi":"10.1109/ICPR.2014.555","DOIUrl":"https://doi.org/10.1109/ICPR.2014.555","url":null,"abstract":"The Brain Extraction Tool (BET) developed by Smith is widely used for brain segmentation due to its simplicity, accuracy and insensitivity to parameter settings. However, it typically requires a large number of iterations to generate acceptable results. It also sometimes fails to recognize boundaries of the brain. Moreover, obvious under-segmentation occurs for some datasets. In this paper, we present an improved BET method where at each iteration, we enhance the vertex displacement, add a new search path and embed an independent surface reconstruction process. These strategies lead to much faster convergence. Furthermore, a scheme based on fuzzy c-means is proposed to refine the segmentation. Experimental results based on various datsets demonstrated that the proposed method significantly outperforms the original BET and other competing methods.","PeriodicalId":142159,"journal":{"name":"2014 22nd International Conference on Pattern Recognition","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134214396","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}
To get high recognition accuracy, we should train the recognizer with sufficient training data to capture characteristics of various handwriting styles and all possible occurring words. However, in most of the cases, available training data are not satisfactory and enough, especially for unseen data. In this paper, we try to improve the recognition accuracy for unseen data with randomly selected training data, by splitting the training data into two parts based on trigrams and training two recognizers separately. We also propose a modified version of token passing algorithm, which makes use of the outputs of the two recognizers to improve the recognition accuracy.
{"title":"Unconstrained Handwritten Word Recognition Based on Trigrams Using BLSTM","authors":"Xi Zhang, C. Tan","doi":"10.1109/ICPR.2014.502","DOIUrl":"https://doi.org/10.1109/ICPR.2014.502","url":null,"abstract":"To get high recognition accuracy, we should train the recognizer with sufficient training data to capture characteristics of various handwriting styles and all possible occurring words. However, in most of the cases, available training data are not satisfactory and enough, especially for unseen data. In this paper, we try to improve the recognition accuracy for unseen data with randomly selected training data, by splitting the training data into two parts based on trigrams and training two recognizers separately. We also propose a modified version of token passing algorithm, which makes use of the outputs of the two recognizers to improve the recognition accuracy.","PeriodicalId":142159,"journal":{"name":"2014 22nd International Conference on Pattern Recognition","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115434997","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}
Kimin Yun, Hawook Jeong, K. M. Yi, S. Kim, J. Choi
This paper presents a novel method for modeling of interaction among multiple moving objects to detect traffic accidents. The proposed method to model object interactions is motivated by the motion of water waves responding to moving objects on water surface. The shape of the water surface is modeled in a field form using Gaussian kernels, which is referred to as the Motion Interaction Field (MIF). By utilizing the symmetric properties of the MIF, we detect and localize traffic accidents without solving complex vehicle tracking problems. Experimental results show that our method outperforms the existing works in detecting and localizing traffic accidents.
{"title":"Motion Interaction Field for Accident Detection in Traffic Surveillance Video","authors":"Kimin Yun, Hawook Jeong, K. M. Yi, S. Kim, J. Choi","doi":"10.1109/ICPR.2014.528","DOIUrl":"https://doi.org/10.1109/ICPR.2014.528","url":null,"abstract":"This paper presents a novel method for modeling of interaction among multiple moving objects to detect traffic accidents. The proposed method to model object interactions is motivated by the motion of water waves responding to moving objects on water surface. The shape of the water surface is modeled in a field form using Gaussian kernels, which is referred to as the Motion Interaction Field (MIF). By utilizing the symmetric properties of the MIF, we detect and localize traffic accidents without solving complex vehicle tracking problems. Experimental results show that our method outperforms the existing works in detecting and localizing traffic accidents.","PeriodicalId":142159,"journal":{"name":"2014 22nd International Conference on Pattern Recognition","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123875585","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}
Sparse coding has been used for target appearance modeling and applied successfully in visual tracking. However, noise may be inevitably introduced into the representation due to background clutter. To cope with this problem, we propose a saliency weighted sparse coding appearance model for visual tracking. Firstly, a spectral filtering based visual attention computational model, which combines both bottom-up and top-down visual attention, is proposed to calculate saliency map. Secondly, pooling operation in sparse coding is weighted by calculated saliency map to help target representation focus on distinctive features and suppress background clutter. Extensive experiments on a recently proposed tracking benchmark demonstrate that the proposed algorithm outperforms state-of-the-art methods in tracking objects under background clutter.
{"title":"Visual Tracking via Saliency Weighted Sparse Coding Appearance Model","authors":"Wanyi Li, Peng Wang, Hong Qiao","doi":"10.1109/ICPR.2014.701","DOIUrl":"https://doi.org/10.1109/ICPR.2014.701","url":null,"abstract":"Sparse coding has been used for target appearance modeling and applied successfully in visual tracking. However, noise may be inevitably introduced into the representation due to background clutter. To cope with this problem, we propose a saliency weighted sparse coding appearance model for visual tracking. Firstly, a spectral filtering based visual attention computational model, which combines both bottom-up and top-down visual attention, is proposed to calculate saliency map. Secondly, pooling operation in sparse coding is weighted by calculated saliency map to help target representation focus on distinctive features and suppress background clutter. Extensive experiments on a recently proposed tracking benchmark demonstrate that the proposed algorithm outperforms state-of-the-art methods in tracking objects under background clutter.","PeriodicalId":142159,"journal":{"name":"2014 22nd International Conference on Pattern Recognition","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123616885","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 novel method of calibrating non-overlapping RGB-D cameras using one chessboard fixed with a laser pointer. A laser pointer is fixed at one calibration board so that its pose at the coordinate system of the calibration board can be obtained easily. While one of the RGB-D cameras observes the calibration board fixed with the laser pointer, the laser pointer project a spot to the scene which is observed by the other. Thus, two 3D points, respectively located in the field of views of the two RGB-D cameras, are connected by a laser ray. The relative pose of two RGB-D cameras can be estimated through this collinear constraint. The experiment results show the effectiveness of the proposed method.
{"title":"Calibrating Non-overlapping RGB-D Cameras","authors":"Wuhe Zou, Shigang Li","doi":"10.1109/ICPR.2014.720","DOIUrl":"https://doi.org/10.1109/ICPR.2014.720","url":null,"abstract":"In this paper, we propose a novel method of calibrating non-overlapping RGB-D cameras using one chessboard fixed with a laser pointer. A laser pointer is fixed at one calibration board so that its pose at the coordinate system of the calibration board can be obtained easily. While one of the RGB-D cameras observes the calibration board fixed with the laser pointer, the laser pointer project a spot to the scene which is observed by the other. Thus, two 3D points, respectively located in the field of views of the two RGB-D cameras, are connected by a laser ray. The relative pose of two RGB-D cameras can be estimated through this collinear constraint. The experiment results show the effectiveness of the proposed method.","PeriodicalId":142159,"journal":{"name":"2014 22nd International Conference on Pattern Recognition","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126173662","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 study we argue that the traditional approach of evaluating the information quality of an anonymized (or otherwise modified) dataset is questionable. We propose a novel and simple approach to evaluate the information quality of a modified dataset, and thereby the quality of techniques that modify data. We carry out experiments on eleven datasets and the empirical results strongly support our arguments. We also present some supplementary measures to our approach that provide additional insight into the information quality of modified data.
{"title":"Quality Evaluation of an Anonymized Dataset","authors":"Sam Fletcher, M. Islam","doi":"10.1109/ICPR.2014.618","DOIUrl":"https://doi.org/10.1109/ICPR.2014.618","url":null,"abstract":"In this study we argue that the traditional approach of evaluating the information quality of an anonymized (or otherwise modified) dataset is questionable. We propose a novel and simple approach to evaluate the information quality of a modified dataset, and thereby the quality of techniques that modify data. We carry out experiments on eleven datasets and the empirical results strongly support our arguments. We also present some supplementary measures to our approach that provide additional insight into the information quality of modified data.","PeriodicalId":142159,"journal":{"name":"2014 22nd International Conference on Pattern Recognition","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122125993","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 novel face recognition approach using 3D directional corner points (3D DCPs). Traditionally, points and meshes are applied to represent and match 3D shapes. Here we represent 3D surfaces by 3D DCPs derived from ridge and valley curves. Then we develop a 3D DCP matching method to compute the similarity of two different 3D surfaces. This representation, along with the similarity metric can effectively integrate structural and spatial information on 3D surfaces. The added information can provide more and better discriminative power for object recognition. It strengthens and improves the matching process of similar 3D objects such as faces. To evaluate the performance of our method for 3D face recognition, we have performed experiments on Face Recognition Grand Challenge v2.0 database (FRGC v2.0) and resulted in a rank-one recognition rate of 97.1%. This study demonstrates that 3D DCPs provides a new solution for 3D face recognition, which may also find its application in general 3D object representation and recognition.
{"title":"Face Recognition Using 3D Directional Corner Points","authors":"Xun Yu, Yongsheng Gao, J. Zhou","doi":"10.1109/ICPR.2014.483","DOIUrl":"https://doi.org/10.1109/ICPR.2014.483","url":null,"abstract":"In this paper, we present a novel face recognition approach using 3D directional corner points (3D DCPs). Traditionally, points and meshes are applied to represent and match 3D shapes. Here we represent 3D surfaces by 3D DCPs derived from ridge and valley curves. Then we develop a 3D DCP matching method to compute the similarity of two different 3D surfaces. This representation, along with the similarity metric can effectively integrate structural and spatial information on 3D surfaces. The added information can provide more and better discriminative power for object recognition. It strengthens and improves the matching process of similar 3D objects such as faces. To evaluate the performance of our method for 3D face recognition, we have performed experiments on Face Recognition Grand Challenge v2.0 database (FRGC v2.0) and resulted in a rank-one recognition rate of 97.1%. This study demonstrates that 3D DCPs provides a new solution for 3D face recognition, which may also find its application in general 3D object representation and recognition.","PeriodicalId":142159,"journal":{"name":"2014 22nd International Conference on Pattern Recognition","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114732181","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}
Most current approaches in action recognition face difficulties that cannot handle recognition of multiple actions, fusion of multiple features, and recognition of action in frame by frame model, incremental learning of new action samples and application of position information of space-time interest points to improve performance simultaneously. In this paper, we propose a novel approach based on Position-Tree that takes advantage of the relationship of the position of joints and interest points. The normalized position of interest points indicates where the movement of body part has occurred. The extraction of local feature encodes the shape of the body part when performing action, justifying body movements. Additionally, we propose a new local descriptor calculating the local energy map from spatial-temporal cuboids around interest point. In our method, there are three steps to recognize an action: (1) extract the skeleton point and space-time interest point, calculating the normalized position according to their relationships with joint position, (2) extract the LEM (Local Energy Map) descriptor around interest point, (3) recognize these local features through non-parametric nearest neighbor and label an action by voting those local features. The proposed approach is tested on publicly available MSRAction3D dataset, demonstrating the advantages and the state-of-art performance of the proposed method.
目前大多数动作识别方法都面临着无法同时处理多动作识别、多特征融合、逐帧模型动作识别、新动作样本增量学习和时空兴趣点位置信息应用等问题。在本文中，我们提出了一种新的基于位置树的方法，利用关节和兴趣点的位置关系。兴趣点的归一化位置表示身体部位发生运动的位置。局部特征的提取对动作时身体部位的形状进行编码，使身体动作合理化。此外，我们提出了一种新的局部描述子，从兴趣点周围的时空长方体计算局部能量映射。在我们的方法中，动作识别分为三个步骤:(1)提取骨架点和时空兴趣点，根据它们与关节位置的关系计算归一化位置;(2)提取兴趣点周围的LEM (Local Energy Map)描述符;(3)通过非参数最近邻识别这些局部特征，并通过投票对这些局部特征进行标记。在公开可用的MSRAction3D数据集上对该方法进行了测试，证明了该方法的优势和最先进的性能。
{"title":"Position-Based Action Recognition Using High Dimension Index Tree","authors":"Qian Xiao, Jun Cheng, Jun Jiang, Wei Feng","doi":"10.1109/ICPR.2014.753","DOIUrl":"https://doi.org/10.1109/ICPR.2014.753","url":null,"abstract":"Most current approaches in action recognition face difficulties that cannot handle recognition of multiple actions, fusion of multiple features, and recognition of action in frame by frame model, incremental learning of new action samples and application of position information of space-time interest points to improve performance simultaneously. In this paper, we propose a novel approach based on Position-Tree that takes advantage of the relationship of the position of joints and interest points. The normalized position of interest points indicates where the movement of body part has occurred. The extraction of local feature encodes the shape of the body part when performing action, justifying body movements. Additionally, we propose a new local descriptor calculating the local energy map from spatial-temporal cuboids around interest point. In our method, there are three steps to recognize an action: (1) extract the skeleton point and space-time interest point, calculating the normalized position according to their relationships with joint position, (2) extract the LEM (Local Energy Map) descriptor around interest point, (3) recognize these local features through non-parametric nearest neighbor and label an action by voting those local features. The proposed approach is tested on publicly available MSRAction3D dataset, demonstrating the advantages and the state-of-art performance of the proposed method.","PeriodicalId":142159,"journal":{"name":"2014 22nd International Conference on Pattern Recognition","volume":"72 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128759648","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}
Yoshimune Tabuchi, Tomokazu Takahashi, Daisuke Deguchi, I. Ide, H. Murase, Takayuki Kurozumi, K. Kashino
Crowd analysis using cameras has attracted much attention for public safety and marketing. Among techniques of the crowd analysis, we focus on spatial people density estimation which estimates the number of people for each small area in a floor region. However, spatial people density cannot be estimated accurately for an area far from the camera because of the occlusion by people in a closer area. Therefore, we propose a method using a memory based regression method with images captured from cameras from multiple viewpoints. This method is realized by looking up a table that consists of correspondences between people density maps and crowd appearances. Since the crowd appearances include situations where various occlusions occur, an estimation robust to occlusion should be realized. In an experiment, we examined the effectiveness of the proposed method.
{"title":"Spatial People Density Estimation from Multiple Viewpoints by Memory Based Regression","authors":"Yoshimune Tabuchi, Tomokazu Takahashi, Daisuke Deguchi, I. Ide, H. Murase, Takayuki Kurozumi, K. Kashino","doi":"10.1109/ICPR.2014.384","DOIUrl":"https://doi.org/10.1109/ICPR.2014.384","url":null,"abstract":"Crowd analysis using cameras has attracted much attention for public safety and marketing. Among techniques of the crowd analysis, we focus on spatial people density estimation which estimates the number of people for each small area in a floor region. However, spatial people density cannot be estimated accurately for an area far from the camera because of the occlusion by people in a closer area. Therefore, we propose a method using a memory based regression method with images captured from cameras from multiple viewpoints. This method is realized by looking up a table that consists of correspondences between people density maps and crowd appearances. Since the crowd appearances include situations where various occlusions occur, an estimation robust to occlusion should be realized. In an experiment, we examined the effectiveness of the proposed method.","PeriodicalId":142159,"journal":{"name":"2014 22nd International Conference on Pattern Recognition","volume":"94 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132846287","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 address the person reidentification problem by efficient data representation method. Based on the Relaxed Nonnegative matrix factorization (rNMF) which has no sign constraints on the data matrix and the basis matrix, we consider two regularizations to improve the Relaxed NMF, which are the local manifold assumption and a rank constraint. The local manifold assumption helps preserve the geometry structure of the data and the rank constraint helps improve the discrimination and the sparsity of the data representations. When only the manifold regularization is considered, we propose the Relaxed Graph regularized NMF (rGNMF). When both two regularizations are considered, we propose the Relaxed NMF with regularizations (rRNMF). To demonstrate our proposed methods, we run experiments on two different publicly available datasets, showing state-of-the-art or even better results, however, on much lower computational efforts.
{"title":"Person Re-identification Based on Relaxed Nonnegative Matrix Factorization with Regularizations","authors":"Weiya Ren, Guohui Li","doi":"10.1109/ICPR.2014.796","DOIUrl":"https://doi.org/10.1109/ICPR.2014.796","url":null,"abstract":"We address the person reidentification problem by efficient data representation method. Based on the Relaxed Nonnegative matrix factorization (rNMF) which has no sign constraints on the data matrix and the basis matrix, we consider two regularizations to improve the Relaxed NMF, which are the local manifold assumption and a rank constraint. The local manifold assumption helps preserve the geometry structure of the data and the rank constraint helps improve the discrimination and the sparsity of the data representations. When only the manifold regularization is considered, we propose the Relaxed Graph regularized NMF (rGNMF). When both two regularizations are considered, we propose the Relaxed NMF with regularizations (rRNMF). To demonstrate our proposed methods, we run experiments on two different publicly available datasets, showing state-of-the-art or even better results, however, on much lower computational efforts.","PeriodicalId":142159,"journal":{"name":"2014 22nd International Conference on Pattern Recognition","volume":"306 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121223465","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：