Pub Date : 2011-11-01DOI: 10.1109/ACPR.2011.6166546
Takahiro Ota, T. Wada
This paper presents a method of fast and accurate character localization for OCR (Optical Character Reader). We already proposed an acceleration framework of arbitrary classifiers, classifier molding, for real-time verification of characters printed by Industrial Ink Jet Printer (IIJP). In this framework, the behavior of accurate but slow character classifier is learnt by linear regression tree. The resulted classifier is up to 1,500 times faster than the original one but is not fast enough for real-time pyramidal scan of VGA images, which is necessary for scale-free character recognition. For solving this problem, we also proposed CCS (Classification based Character Segmentation). This method finds character arrangement that maximizes the sum of the likelihood of character regions assuming that all characters are horizontally aligned with almost regular intervals. This assumption is not always true even for the characters printed by IIJP. For solving this problem, we extended the idea of CCS to arbitrary located characters. Our method first generates character-region candidates based on local elliptical regions, named Fast-Hessian-Affine regions, and finds most likely character arrangement. Through experiments, we confirmed that our method quickly and accurately recognizes non-uniformly arranged characters.
提出了一种快速准确的OCR (Optical character Reader)字符定位方法。我们已经提出了一个任意分类器的加速框架，分类器成型，用于工业喷墨打印机(IIJP)打印的字符的实时验证。在该框架中，通过线性回归树学习准确但速度慢的字符分类器的行为。所得到的分类器比原来的分类器快了1500倍，但对于VGA图像的实时金字塔扫描来说还不够快，这是无比例字符识别所必需的。为了解决这个问题，我们还提出了基于分类的字符分割(CCS)。该方法找到的字符排列，最大限度地提高字符区域的可能性的总和，假设所有字符水平对齐几乎有规则的间隔。即使对于IIJP打印的字符，这个假设也不总是正确的。为了解决这个问题，我们将CCS的理念扩展到任意位置的字符。该方法首先基于局部椭圆区域(Fast-Hessian-Affine region)生成候选字符区域，并找到最可能的字符排列。实验结果表明，该方法能够快速准确地识别非均匀排列字符。
{"title":"Classification based character segmentation guided by Fast-Hessian-Affine regions","authors":"Takahiro Ota, T. Wada","doi":"10.1109/ACPR.2011.6166546","DOIUrl":"https://doi.org/10.1109/ACPR.2011.6166546","url":null,"abstract":"This paper presents a method of fast and accurate character localization for OCR (Optical Character Reader). We already proposed an acceleration framework of arbitrary classifiers, classifier molding, for real-time verification of characters printed by Industrial Ink Jet Printer (IIJP). In this framework, the behavior of accurate but slow character classifier is learnt by linear regression tree. The resulted classifier is up to 1,500 times faster than the original one but is not fast enough for real-time pyramidal scan of VGA images, which is necessary for scale-free character recognition. For solving this problem, we also proposed CCS (Classification based Character Segmentation). This method finds character arrangement that maximizes the sum of the likelihood of character regions assuming that all characters are horizontally aligned with almost regular intervals. This assumption is not always true even for the characters printed by IIJP. For solving this problem, we extended the idea of CCS to arbitrary located characters. Our method first generates character-region candidates based on local elliptical regions, named Fast-Hessian-Affine regions, and finds most likely character arrangement. Through experiments, we confirmed that our method quickly and accurately recognizes non-uniformly arranged characters.","PeriodicalId":287232,"journal":{"name":"The First Asian Conference on Pattern Recognition","volume":"140 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122404767","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 : 2011-11-01DOI: 10.1109/ACPR.2011.6166560
Xin Zhao, Weiqiang Ren, Kaiqi Huang, T. Tan
Bag-of-words (BoW) model is widely used for image classification. Recently, the framework of sparse coding and max pooling proved an effective approach for image classification. Max pooling adopts a winner-take-all strategy. Thus, it can be regarded as a codebook weighting process. The results of this process are the weights of the associated codebook. However, there are high intra-class variations and strong background clutters in many image classification tasks. The weights obtained by max pooling only have limited information. This paper presents a codebook reweighting algorithm using pairwise constraints to improve the performance of sparse coding and max pooling framework. Pairwise constraints are the natural way of encoding the relationships between pairs of images. Therefore, the reweighted codebook is more effective to describe the relevance between pairs of images. An efficient online learning algorithm is presented based on passive-aggressive training strategy. We compare our method with other state-of-the-art methods on Graz-01 & 02 datasets. Experimental results illustrate the effectiveness and efficiency of our method for image classification.
{"title":"Online codebook reweighting using pairwise constraints for image classification","authors":"Xin Zhao, Weiqiang Ren, Kaiqi Huang, T. Tan","doi":"10.1109/ACPR.2011.6166560","DOIUrl":"https://doi.org/10.1109/ACPR.2011.6166560","url":null,"abstract":"Bag-of-words (BoW) model is widely used for image classification. Recently, the framework of sparse coding and max pooling proved an effective approach for image classification. Max pooling adopts a winner-take-all strategy. Thus, it can be regarded as a codebook weighting process. The results of this process are the weights of the associated codebook. However, there are high intra-class variations and strong background clutters in many image classification tasks. The weights obtained by max pooling only have limited information. This paper presents a codebook reweighting algorithm using pairwise constraints to improve the performance of sparse coding and max pooling framework. Pairwise constraints are the natural way of encoding the relationships between pairs of images. Therefore, the reweighted codebook is more effective to describe the relevance between pairs of images. An efficient online learning algorithm is presented based on passive-aggressive training strategy. We compare our method with other state-of-the-art methods on Graz-01 & 02 datasets. Experimental results illustrate the effectiveness and efficiency of our method for image classification.","PeriodicalId":287232,"journal":{"name":"The First Asian Conference on Pattern Recognition","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128948879","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 : 2011-11-01DOI: 10.1109/ACPR.2011.6166589
Jin Zhang, Yonghong Song, Yuanlin Zhang, Xiaobing Wang
This paper presents a novel color quantization method based on Normalized Cut clustering algorithm, in order to generate a quantized image with the minimum loss of information and the maximum compression ratio, which benefits the storage and transmission of the color image. This new method uses a deformed Median Cut algorithm as a coarse partition of color pixels in the RGB color space, and then take the average color of each partition as the representative color of a node to construct a condensed graph. By employing the Normalized Cut clustering algorithm, we could get the palette with defined color number, and then reconstruct the quantized image. Experiments on common used test images demonstrate that our method is very competitive with state-of-the-art color quantization methods in terms of image quality, compression ratio and computation time.
{"title":"A new approach of color image quantization based on Normalized Cut algorithm","authors":"Jin Zhang, Yonghong Song, Yuanlin Zhang, Xiaobing Wang","doi":"10.1109/ACPR.2011.6166589","DOIUrl":"https://doi.org/10.1109/ACPR.2011.6166589","url":null,"abstract":"This paper presents a novel color quantization method based on Normalized Cut clustering algorithm, in order to generate a quantized image with the minimum loss of information and the maximum compression ratio, which benefits the storage and transmission of the color image. This new method uses a deformed Median Cut algorithm as a coarse partition of color pixels in the RGB color space, and then take the average color of each partition as the representative color of a node to construct a condensed graph. By employing the Normalized Cut clustering algorithm, we could get the palette with defined color number, and then reconstruct the quantized image. Experiments on common used test images demonstrate that our method is very competitive with state-of-the-art color quantization methods in terms of image quality, compression ratio and computation time.","PeriodicalId":287232,"journal":{"name":"The First Asian Conference on Pattern Recognition","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134223912","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 : 2011-11-01DOI: 10.1109/ACPR.2011.6166535
Meijuan Yang, Yuan Yuan, Xuelong Li, Pingkun Yan
Deformable models have obtained considerable success in medical image segmentation, due to its ability of capturing the shape variation of the target structure. Boundary feature is used to guide contour deformation, which plays an decisive part in deformable model based segmentation. However, it is still a challenging task to obtain a distinctive image feature to describe the boundaries, since boundaries are not necessarily in accordance with edges or ridges. Another challenge is to infer the shape for the given image appearance. In this paper, the anatomical structures from MR images are aimed to be segmented. First, a new normal vector feature profile (NVFP) is employed to describe the local image appearance of a contour point formed by a series of modified SIFT local descriptors along the normal direction of that point. Second, the shape of the target structure is inferred by matching two image appearances of the test image and learned image appearance. A new match function is designed to incorporate the new NVFP to deformable models. During the optimization procedure of the segmentation algorithm, the nearest neighbor approach is used to compute the displacement of each contour point to guide the global shape deformation. Experimental results on prostate and bladder MR images show that the proposed method has a better performance than the previous method.
{"title":"Designing and selecting features for MR image segmentation","authors":"Meijuan Yang, Yuan Yuan, Xuelong Li, Pingkun Yan","doi":"10.1109/ACPR.2011.6166535","DOIUrl":"https://doi.org/10.1109/ACPR.2011.6166535","url":null,"abstract":"Deformable models have obtained considerable success in medical image segmentation, due to its ability of capturing the shape variation of the target structure. Boundary feature is used to guide contour deformation, which plays an decisive part in deformable model based segmentation. However, it is still a challenging task to obtain a distinctive image feature to describe the boundaries, since boundaries are not necessarily in accordance with edges or ridges. Another challenge is to infer the shape for the given image appearance. In this paper, the anatomical structures from MR images are aimed to be segmented. First, a new normal vector feature profile (NVFP) is employed to describe the local image appearance of a contour point formed by a series of modified SIFT local descriptors along the normal direction of that point. Second, the shape of the target structure is inferred by matching two image appearances of the test image and learned image appearance. A new match function is designed to incorporate the new NVFP to deformable models. During the optimization procedure of the segmentation algorithm, the nearest neighbor approach is used to compute the displacement of each contour point to guide the global shape deformation. Experimental results on prostate and bladder MR images show that the proposed method has a better performance than the previous method.","PeriodicalId":287232,"journal":{"name":"The First Asian Conference on Pattern Recognition","volume":"114 26","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113946008","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 : 2011-11-01DOI: 10.1109/ACPR.2011.6166688
Liwei Liu, Junliang Xing, H. Ai
Multi-view vehicle detection and tracking in crossroads is of fundamental importance in traffic surveillance yet still remains a very challenging task. The view changes of different vehicles and their occlusions in crossroads are two main difficulties that often fail many existing methods. To handle these difficulties, we propose a new method for multi-view vehicle detection and tracking that innovates mainly on two aspects: the two-stage view selection and the dual-layer occlusion handling. For the two-stage view selection, a Multi-Modal Particle Filter (MMPF) is proposed to track vehicles in explicit view, i.e. frontal (rear) view or side view. In the second stage, for the vehicles in inexplicit views, i.e. intermediate views between frontal and side view, spatial-temporal analysis is employed to further decide their views so as to maintain the consistence of view transition. For the dual-layer occlusion handling, a cluster based dedicated vehicle model for partial occlusion and a backward retracking procedure for full occlusion are integrated complementarily to deal with occlusion problems. The two-stage view selection is efficient for fusing multiple detectors, while the dual-layer occlusion handling improves tracking performance effectively. Extensive experiments under different weather conditions, including snowy, sunny and cloudy, demonstrate the effectiveness and efficiency of our method.
{"title":"Multi-view vehicle detection and tracking in crossroads","authors":"Liwei Liu, Junliang Xing, H. Ai","doi":"10.1109/ACPR.2011.6166688","DOIUrl":"https://doi.org/10.1109/ACPR.2011.6166688","url":null,"abstract":"Multi-view vehicle detection and tracking in crossroads is of fundamental importance in traffic surveillance yet still remains a very challenging task. The view changes of different vehicles and their occlusions in crossroads are two main difficulties that often fail many existing methods. To handle these difficulties, we propose a new method for multi-view vehicle detection and tracking that innovates mainly on two aspects: the two-stage view selection and the dual-layer occlusion handling. For the two-stage view selection, a Multi-Modal Particle Filter (MMPF) is proposed to track vehicles in explicit view, i.e. frontal (rear) view or side view. In the second stage, for the vehicles in inexplicit views, i.e. intermediate views between frontal and side view, spatial-temporal analysis is employed to further decide their views so as to maintain the consistence of view transition. For the dual-layer occlusion handling, a cluster based dedicated vehicle model for partial occlusion and a backward retracking procedure for full occlusion are integrated complementarily to deal with occlusion problems. The two-stage view selection is efficient for fusing multiple detectors, while the dual-layer occlusion handling improves tracking performance effectively. Extensive experiments under different weather conditions, including snowy, sunny and cloudy, demonstrate the effectiveness and efficiency of our method.","PeriodicalId":287232,"journal":{"name":"The First Asian Conference on Pattern Recognition","volume":"24 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114033755","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 : 2011-11-01DOI: 10.1109/ACPR.2011.6166528
Zhipeng Wang, M. Kagesawa, Shintaro Ono, A. Banno, K. Ikeuchi
Automobile navigation in tunnel environment is challenging. GPS sensors and ordinary cameras can't function effectively. For navigation, infrared cameras are installed on top of our experimental vehicle, and here we propose an efficient object detection method to detect emergency lights from the collected data in tunnel environment. The proposed method firstly detects keypoints by setting thresholds for intensity of uniformly sampled points. Each keypoint is then verified by the appearance of its surrounding sub-image. After clustering the keypoints which satisfy the verification, the method verifies the keypoint clusters by their appearance and temporal information. Though the later steps are time-consuming, they deal with very few instances. And this improves the efficiency of the method, while not losing effectiveness of the appearance and temporal information. Thus the method gives promising results in real time. Detection performance and efficiency are verified by experiments carried on challenging real data.
{"title":"Emergency light detection in tunnel environment: An efficient method","authors":"Zhipeng Wang, M. Kagesawa, Shintaro Ono, A. Banno, K. Ikeuchi","doi":"10.1109/ACPR.2011.6166528","DOIUrl":"https://doi.org/10.1109/ACPR.2011.6166528","url":null,"abstract":"Automobile navigation in tunnel environment is challenging. GPS sensors and ordinary cameras can't function effectively. For navigation, infrared cameras are installed on top of our experimental vehicle, and here we propose an efficient object detection method to detect emergency lights from the collected data in tunnel environment. The proposed method firstly detects keypoints by setting thresholds for intensity of uniformly sampled points. Each keypoint is then verified by the appearance of its surrounding sub-image. After clustering the keypoints which satisfy the verification, the method verifies the keypoint clusters by their appearance and temporal information. Though the later steps are time-consuming, they deal with very few instances. And this improves the efficiency of the method, while not losing effectiveness of the appearance and temporal information. Thus the method gives promising results in real time. Detection performance and efficiency are verified by experiments carried on challenging real data.","PeriodicalId":287232,"journal":{"name":"The First Asian Conference on Pattern Recognition","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122887984","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 : 2011-11-01DOI: 10.1109/ACPR.2011.6166595
T. Saitoh
This paper presents a high-level real-time lip reading system that can recognize both fixed phrase and its combination. Lip reading provides an important means for realizing a communication support interface for speech handicaps. The approach is based on the Viola-Jones face detector, lip extraction based on active appearance model, automatic utterance section detector, and phrase classifier using DP matching. Our system has two unique ideas; combined phrase recognition, and remove false recognition phrase from a target list. These ideas are simple but efficient in practical use. We demonstrated our system with five subjects and confirmed the usefulness.
{"title":"Real-time lip reading system for fixed phrase and its combination","authors":"T. Saitoh","doi":"10.1109/ACPR.2011.6166595","DOIUrl":"https://doi.org/10.1109/ACPR.2011.6166595","url":null,"abstract":"This paper presents a high-level real-time lip reading system that can recognize both fixed phrase and its combination. Lip reading provides an important means for realizing a communication support interface for speech handicaps. The approach is based on the Viola-Jones face detector, lip extraction based on active appearance model, automatic utterance section detector, and phrase classifier using DP matching. Our system has two unique ideas; combined phrase recognition, and remove false recognition phrase from a target list. These ideas are simple but efficient in practical use. We demonstrated our system with five subjects and confirmed the usefulness.","PeriodicalId":287232,"journal":{"name":"The First Asian Conference on Pattern Recognition","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128762869","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 : 2011-11-01DOI: 10.1109/ACPR.2011.6166693
Le Thanh Hoan, Youngjae Chun, Kyoungsu Oh
Image mosaic is a large image assembled from many smaller tiles which one tile itself is an actual image. In this research, we introduce an efficient method to make image mosaic. Our method is based on Log-polar mapping which enables us to detect the color and shape change. We also successfully make an image mosaic version by exploiting GPU power. Our algorithm is simple, easy to implement, gives better result than conventional method and can be improved to higher precision.
{"title":"Image mosaic using Log-polar binning","authors":"Le Thanh Hoan, Youngjae Chun, Kyoungsu Oh","doi":"10.1109/ACPR.2011.6166693","DOIUrl":"https://doi.org/10.1109/ACPR.2011.6166693","url":null,"abstract":"Image mosaic is a large image assembled from many smaller tiles which one tile itself is an actual image. In this research, we introduce an efficient method to make image mosaic. Our method is based on Log-polar mapping which enables us to detect the color and shape change. We also successfully make an image mosaic version by exploiting GPU power. Our algorithm is simple, easy to implement, gives better result than conventional method and can be improved to higher precision.","PeriodicalId":287232,"journal":{"name":"The First Asian Conference on Pattern Recognition","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129394249","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 : 2011-11-01DOI: 10.1109/ACPR.2011.6166689
Atsushi Irie, M. Takagiwa, Kozo Moriyama, Takayoshi Yamashita
There are many methods based on shape and texture models for detecting eye and mouth contour points from facial images. They reduce the false positive rate by utilizing a global model and adapting it for a given face. Changes to facial expressions are coupled with changes to the shapes of eyes and mouth, and a global facial model in itself cannot be adapted to all human facial expressions. Therefore, a hierarchical model fitting approach has been developed, whereby the global fitting captures the facial shape using the global model and the local fitting captures the each facial parts using these local models. This can detect facial contours with high accuracy for expressions to which the global model cannot be adapted.
{"title":"Improvements to facial contour detection by hierarchical fitting and regression","authors":"Atsushi Irie, M. Takagiwa, Kozo Moriyama, Takayoshi Yamashita","doi":"10.1109/ACPR.2011.6166689","DOIUrl":"https://doi.org/10.1109/ACPR.2011.6166689","url":null,"abstract":"There are many methods based on shape and texture models for detecting eye and mouth contour points from facial images. They reduce the false positive rate by utilizing a global model and adapting it for a given face. Changes to facial expressions are coupled with changes to the shapes of eyes and mouth, and a global facial model in itself cannot be adapted to all human facial expressions. Therefore, a hierarchical model fitting approach has been developed, whereby the global fitting captures the facial shape using the global model and the local fitting captures the each facial parts using these local models. This can detect facial contours with high accuracy for expressions to which the global model cannot be adapted.","PeriodicalId":287232,"journal":{"name":"The First Asian Conference on Pattern Recognition","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126902199","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 : 2011-11-01DOI: 10.1109/ACPR.2011.6166708
Yi-fei Xu, He-lei Wu
We consider the problem of recognizing human faces with varying expression and illumination, and a novel confidence index based block linear regression classification method is proposed. Our approach divides images into blocks, and each block is identified using the linear regression classifier separately. We develop a confidence index model to measure the recognition confidence of each block, and the final decision is achieved by aggregating individual results with the designed Bayesian decision fusion algorithm. The performances of our approach and conventional algorithms are evaluated under conditions of varying expression and illumination using benchmark databases, improvements demonstrate the proposed approach is robustness to both expression and illumination variations.
{"title":"Decision fusion for block linear regression classification based on confidence index","authors":"Yi-fei Xu, He-lei Wu","doi":"10.1109/ACPR.2011.6166708","DOIUrl":"https://doi.org/10.1109/ACPR.2011.6166708","url":null,"abstract":"We consider the problem of recognizing human faces with varying expression and illumination, and a novel confidence index based block linear regression classification method is proposed. Our approach divides images into blocks, and each block is identified using the linear regression classifier separately. We develop a confidence index model to measure the recognition confidence of each block, and the final decision is achieved by aggregating individual results with the designed Bayesian decision fusion algorithm. The performances of our approach and conventional algorithms are evaluated under conditions of varying expression and illumination using benchmark databases, improvements demonstrate the proposed approach is robustness to both expression and illumination variations.","PeriodicalId":287232,"journal":{"name":"The First Asian Conference on Pattern Recognition","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125790024","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：