Pub Date : 2010-05-01DOI: 10.1109/TSMCA.2010.2040272
J. Hsieh, Chi-Hung Chuang, Sin-Yu Chen, Chih-Chiang Chen, Kuo-Chin Fan
This paper presents a new segmentation algorithm to segment a body posture into different body parts using the technique of triangulation. For well analyzing each posture, we first propose a triangulation-based method to triangulate it to different triangle meshes. Then, we use a depth-first search scheme to find a spanning tree as its skeleton feature from the set of triangulation meshes. The triangulation-based scheme to extract important skeleton features has more robustness and effectiveness than other silhouette-based approaches. Then, different body parts can be roughly extracted by removing all the branching points from the spanning tree. A model-driven technique is then proposed for more accurately segmenting a human body into semantic parts. This technique uses the concept of Gaussian mixture model (GMM) to model different visual properties of different body parts. Then, a suitable segmentation scheme can be driven by classifying these models using their skeletons. Experimental results have proved that the proposed method is robust, accurate, and powerful in body part segmentation
{"title":"Segmentation of Human Body Parts Using Deformable Triangulation","authors":"J. Hsieh, Chi-Hung Chuang, Sin-Yu Chen, Chih-Chiang Chen, Kuo-Chin Fan","doi":"10.1109/TSMCA.2010.2040272","DOIUrl":"https://doi.org/10.1109/TSMCA.2010.2040272","url":null,"abstract":"This paper presents a new segmentation algorithm to segment a body posture into different body parts using the technique of triangulation. For well analyzing each posture, we first propose a triangulation-based method to triangulate it to different triangle meshes. Then, we use a depth-first search scheme to find a spanning tree as its skeleton feature from the set of triangulation meshes. The triangulation-based scheme to extract important skeleton features has more robustness and effectiveness than other silhouette-based approaches. Then, different body parts can be roughly extracted by removing all the branching points from the spanning tree. A model-driven technique is then proposed for more accurately segmenting a human body into semantic parts. This technique uses the concept of Gaussian mixture model (GMM) to model different visual properties of different body parts. Then, a suitable segmentation scheme can be driven by classifying these models using their skeletons. Experimental results have proved that the proposed method is robust, accurate, and powerful in body part segmentation","PeriodicalId":236033,"journal":{"name":"18th International Conference on Pattern Recognition (ICPR'06)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124191099","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 a practical video encoder, a video sequence obtained from a CCD camera inevitably conveys noise, which degrades not only image quality but also coding efficiency. Based on the statistic analysis of noise signal, a noise variance adaptive two-stage successive elimination algorithm (NVA-SEA) for block motion estimation is presented. Simulation results demonstrate that the proposed algorithm can get close performance to the full search, while the computation time has been significantly reduced
{"title":"Noise Variance Adaptive SEA for Motion Estimation: A Two-Stage Schema","authors":"Weigang Chen","doi":"10.1109/ICPR.2006.859","DOIUrl":"https://doi.org/10.1109/ICPR.2006.859","url":null,"abstract":"In a practical video encoder, a video sequence obtained from a CCD camera inevitably conveys noise, which degrades not only image quality but also coding efficiency. Based on the statistic analysis of noise signal, a noise variance adaptive two-stage successive elimination algorithm (NVA-SEA) for block motion estimation is presented. Simulation results demonstrate that the proposed algorithm can get close performance to the full search, while the computation time has been significantly reduced","PeriodicalId":236033,"journal":{"name":"18th International Conference on Pattern Recognition (ICPR'06)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116439635","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 propose a hybrid system for Bangla handwritten numeral recognition based on partially labeled two-layer SOM and MLP classifiers. Partially labeled mechanism is introduced to the Kohonen's SOM for reducing recognition error rate, and two-layer structure is applied for improving the performance of the SOM classifier. The directional and density features are utilized in our system, and the partially labeled SOM is applied first. In the case that the character cannot be recognized by the partially labeled SOM, it will be feed to a multi-layer perceptron classifier for further processing. The experiments on the Bangla handwritten numeral samples captured from real envelopes have found that the hybrid system achieves 96.7% correct recognition rate
{"title":"A Hybrid Recognition Scheme Based on Partially Labeled SOM and MLP","authors":"Shujing Lu, Chunyun Xiao, Yue Lu","doi":"10.1109/ICPR.2006.85","DOIUrl":"https://doi.org/10.1109/ICPR.2006.85","url":null,"abstract":"We propose a hybrid system for Bangla handwritten numeral recognition based on partially labeled two-layer SOM and MLP classifiers. Partially labeled mechanism is introduced to the Kohonen's SOM for reducing recognition error rate, and two-layer structure is applied for improving the performance of the SOM classifier. The directional and density features are utilized in our system, and the partially labeled SOM is applied first. In the case that the character cannot be recognized by the partially labeled SOM, it will be feed to a multi-layer perceptron classifier for further processing. The experiments on the Bangla handwritten numeral samples captured from real envelopes have found that the hybrid system achieves 96.7% correct recognition rate","PeriodicalId":236033,"journal":{"name":"18th International Conference on Pattern Recognition (ICPR'06)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128539278","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 need to tell human and machines apart has surged due to abuse of automated `bots'. However, several textual-image-based CAPTCHAs have been defeated recently, calling for the development of new anti-automation schemes. In this paper, we propose a simple yet effective visual CAPTCHA test by exchanging the content of non-overlapping regions in an image. We give in-depth analysis regarding the choice of parameter and image database during the test generation phase. We also contemplate possible ways, including: 1) random guess, 2) collect and match, and 3) image segmentation, to defeat the proposed test and provide counter-measures when necessary. Preliminary experimental results have validated the efficacy of the proposed CAPTCHA, although we expect that a large-scale experiment to collect and analyze user responses contribute to optimal parameter settings
{"title":"A Captcha Mechanism By Exchange Image Blocks","authors":"W. Liao","doi":"10.1109/ICPR.2006.40","DOIUrl":"https://doi.org/10.1109/ICPR.2006.40","url":null,"abstract":"The need to tell human and machines apart has surged due to abuse of automated `bots'. However, several textual-image-based CAPTCHAs have been defeated recently, calling for the development of new anti-automation schemes. In this paper, we propose a simple yet effective visual CAPTCHA test by exchanging the content of non-overlapping regions in an image. We give in-depth analysis regarding the choice of parameter and image database during the test generation phase. We also contemplate possible ways, including: 1) random guess, 2) collect and match, and 3) image segmentation, to defeat the proposed test and provide counter-measures when necessary. Preliminary experimental results have validated the efficacy of the proposed CAPTCHA, although we expect that a large-scale experiment to collect and analyze user responses contribute to optimal parameter settings","PeriodicalId":236033,"journal":{"name":"18th International Conference on Pattern Recognition (ICPR'06)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130201453","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 pair of algorithms to segment olive groves and recognize its individual trees in high spatial resolution remotely sensed images is presented. The developed algorithms are applied with success by exploiting the typical spatial patterns presented by this cover and are mainly based on mathematical morphology operators
{"title":"Morphological recognition of the spatial patterns of olive trees","authors":"P. Pina, T. Barata, L. Bandeira","doi":"10.1109/ICPR.2006.811","DOIUrl":"https://doi.org/10.1109/ICPR.2006.811","url":null,"abstract":"A pair of algorithms to segment olive groves and recognize its individual trees in high spatial resolution remotely sensed images is presented. The developed algorithms are applied with success by exploiting the typical spatial patterns presented by this cover and are mainly based on mathematical morphology operators","PeriodicalId":236033,"journal":{"name":"18th International Conference on Pattern Recognition (ICPR'06)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114997971","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 volumetric shape from silhouette algorithm based on a centripetal pentahedron model. The algorithm first partitions the space with a set of infinite triangular pyramids derived from a geodesic sphere. Then the pyramids are cut by silhouettes into a set of pentahedrons, which together constitute the centripetal pentahedron model of the visual hull. This process is accelerated by pre-computed polar silhouette graphs (PSGs) and reduced PSGs. Finally a mesh surface model is extracted by marching pentahedrons. Our algorithm has the advantages of robustness, speediness and preciseness
{"title":"A Novel Volumetric Shape from Silhouette Algorithm Based on a Centripetal Pentahedron Model","authors":"Xin Liu, H. Yao, Guilin Yao, Wen Gao","doi":"10.1109/ICPR.2006.146","DOIUrl":"https://doi.org/10.1109/ICPR.2006.146","url":null,"abstract":"In this paper we present a novel volumetric shape from silhouette algorithm based on a centripetal pentahedron model. The algorithm first partitions the space with a set of infinite triangular pyramids derived from a geodesic sphere. Then the pyramids are cut by silhouettes into a set of pentahedrons, which together constitute the centripetal pentahedron model of the visual hull. This process is accelerated by pre-computed polar silhouette graphs (PSGs) and reduced PSGs. Finally a mesh surface model is extracted by marching pentahedrons. Our algorithm has the advantages of robustness, speediness and preciseness","PeriodicalId":236033,"journal":{"name":"18th International Conference on Pattern Recognition (ICPR'06)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115311082","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}
Chung-Hao Chen, Chang Cheng, D. Page, A. Koschan, M. Abidi
This paper describes a robotic application that tracks a moving object by utilizing a mobile robot with multiple sensors. The robotic platform uses a visual camera to sense the movement of the desired object and a range sensor to help the robot detect and then avoid obstacles in real time while continuing to track and follow the desired object. In terms of real-time obstacle avoidance capacity, this paper also presents a modified potential field algorithm called dynamic goal potential field algorithm (DGPF) for this robotic application specifically. Experimental results show that the robotic and intelligent system can fulfill the requirements of tracking an object and avoiding obstacles simultaneously when the object is moving
{"title":"A Moving Object Tracked by A Mobile Robot with Real-Time Obstacles Avoidance Capacity","authors":"Chung-Hao Chen, Chang Cheng, D. Page, A. Koschan, M. Abidi","doi":"10.1109/ICPR.2006.106","DOIUrl":"https://doi.org/10.1109/ICPR.2006.106","url":null,"abstract":"This paper describes a robotic application that tracks a moving object by utilizing a mobile robot with multiple sensors. The robotic platform uses a visual camera to sense the movement of the desired object and a range sensor to help the robot detect and then avoid obstacles in real time while continuing to track and follow the desired object. In terms of real-time obstacle avoidance capacity, this paper also presents a modified potential field algorithm called dynamic goal potential field algorithm (DGPF) for this robotic application specifically. Experimental results show that the robotic and intelligent system can fulfill the requirements of tracking an object and avoiding obstacles simultaneously when the object is moving","PeriodicalId":236033,"journal":{"name":"18th International Conference on Pattern Recognition (ICPR'06)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115383749","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 coupon classification system based on image vector matching. This method features following two points. (1) Extract a feature vector from a gray-scale image using a feature map which is derived from training coupon images. (2) Classify a coupon image by adaptive mask distance to cope with the recognition difficulty such as partial cutting of coupon and putting stamp on it. We have implemented this method and experimented with collected samples. It achieved 100% of recognition rates, processing speed 11.76msec/sheet to 969 images for 42 kinds of coupon samples
{"title":"A Coupon Classification Method Based on Adaptive Image Vector Matching","authors":"T. Nagasaki, K. Marukawa, T. Kagehiro, H. Sako","doi":"10.1109/ICPR.2006.58","DOIUrl":"https://doi.org/10.1109/ICPR.2006.58","url":null,"abstract":"This paper describes a coupon classification system based on image vector matching. This method features following two points. (1) Extract a feature vector from a gray-scale image using a feature map which is derived from training coupon images. (2) Classify a coupon image by adaptive mask distance to cope with the recognition difficulty such as partial cutting of coupon and putting stamp on it. We have implemented this method and experimented with collected samples. It achieved 100% of recognition rates, processing speed 11.76msec/sheet to 969 images for 42 kinds of coupon samples","PeriodicalId":236033,"journal":{"name":"18th International Conference on Pattern Recognition (ICPR'06)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115396557","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 main objective of the work presented here is to introduce a supervised, nonlinear dimensionality reduction technique which performs well-known linear discriminant analysis in a local way and which is able to provide a powerful mapping with less computational effort than other nonlinear reduction methods. Additionally, because of the close connection of the new approach to Fisher's LDA, it is more clear that it acts discriminatively, which is not immediately apparent from previous formulations. The method makes use of the optimal scoring framework advocated by Hastie et al. and it is coined local discriminant analysis (lDA)
{"title":"Local Discriminant Analysis","authors":"M. Loog, D. Ridder","doi":"10.1109/ICPR.2006.769","DOIUrl":"https://doi.org/10.1109/ICPR.2006.769","url":null,"abstract":"The main objective of the work presented here is to introduce a supervised, nonlinear dimensionality reduction technique which performs well-known linear discriminant analysis in a local way and which is able to provide a powerful mapping with less computational effort than other nonlinear reduction methods. Additionally, because of the close connection of the new approach to Fisher's LDA, it is more clear that it acts discriminatively, which is not immediately apparent from previous formulations. The method makes use of the optimal scoring framework advocated by Hastie et al. and it is coined local discriminant analysis (lDA)","PeriodicalId":236033,"journal":{"name":"18th International Conference on Pattern Recognition (ICPR'06)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115495822","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 compares two different methods to combine feature streams to improve the performance of offline handwritten text line recognition systems. In both methods a pixel-based and a geometric feature stream are combined. The first method integrates the feature streams at an early stage whereas in the second method a combination step at the decision level is applied. In the experiments, the early integration approach outperforms the decision level combination as well as recognisers built from the individual feature streams
{"title":"Early feature stream integration versus decision level combination in a multiple classifier system for text line recognition","authors":"Roman Bertolami, H. Bunke","doi":"10.1109/ICPR.2006.466","DOIUrl":"https://doi.org/10.1109/ICPR.2006.466","url":null,"abstract":"This paper compares two different methods to combine feature streams to improve the performance of offline handwritten text line recognition systems. In both methods a pixel-based and a geometric feature stream are combined. The first method integrates the feature streams at an early stage whereas in the second method a combination step at the decision level is applied. In the experiments, the early integration approach outperforms the decision level combination as well as recognisers built from the individual feature streams","PeriodicalId":236033,"journal":{"name":"18th International Conference on Pattern Recognition (ICPR'06)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115629085","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：