Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.最新文献

Computational analysis of mannerism gestures 习惯手势的计算分析

Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-09-20 DOI: 10.1109/ICPR.2004.1334685

K. Kahol, P. Tripathi, S. Panchanathan

{"title":"Computational analysis of mannerism gestures","authors":"K. Kahol, P. Tripathi, S. Panchanathan","doi":"10.1109/ICPR.2004.1334685","DOIUrl":"https://doi.org/10.1109/ICPR.2004.1334685","url":null,"abstract":"Humans perform various gestures in everyday life. While some of these gestures are typically well understood amongst a community (such as \"hello\" and \"goodbye\"), many gestures and movement are typical of an individual's style, body language or mannerisms. Examples of such gestures include the manner is which a person laughs, hand gestures used to converse or the manner in which a person performs a dance sequence. Individuals possess a large vocabulary of mannerism gestures. Conventional modeling of gestures as a series of poses for the purpose of automatically recognizing gestures is inadequate for modeling mannerism gestures. In this paper we propose a novel method to model mannerism gestures. Gestures are modeled as a sequence of events that take place within the segments and the joints of the human body. Each gesture is then represented in an event-driven coupled hidden Markov model (HMM) as a sequence of events, occurring in the various segments and joints. The inherent advantage of using an event-driven coupled-HMM (instead of a pose-driven HMM) is that there is no need to add states to represent more complex gestures or increase the states for addition of another individual. When this model was tested on a library of 185 gestures, created by 7 subjects, the algorithm achieved an average recognition accuracy of 90.2%.","PeriodicalId":335842,"journal":{"name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121636359","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}

引用次数: 13

Generating omnifocus images using graph cuts and a new focus measure 使用图形切割和一种新的焦点测量方法生成全焦图像

Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-09-20 DOI: 10.1109/ICPR.2004.1333868

N. Xu, K. Tan, H. Arora, N. Ahuja

引用次数: 16

Real time facial expression recognition with AdaBoost 实时面部表情识别与AdaBoost

Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-09-20 DOI: 10.1109/ICPR.2004.1334680

Yubo Wang, H. Ai, Bo Wu, Chang Huang

引用次数: 141

Cancelable biometric filters for face recognition 人脸识别的可取消生物特征过滤器

Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-09-20 DOI: 10.1109/ICPR.2004.1334679

M. Savvides, B. Kumar, P. Khosla

{"title":"Cancelable biometric filters for face recognition","authors":"M. Savvides, B. Kumar, P. Khosla","doi":"10.1109/ICPR.2004.1334679","DOIUrl":"https://doi.org/10.1109/ICPR.2004.1334679","url":null,"abstract":"In this paper, we address the issue of producing cancelable biometric templates; a necessary feature in the deployment of any biometric authentication system. We propose a novel scheme that encrypts the training images used to synthesize the single minimum average correlation energy filter for biometric authentication. We show theoretically that convolving the training images with any random convolution kernel prior to building the biometric filter does not change the resulting correlation output peak-to-sidelobe ratios, thus preserving the authentication performance. However, different templates can be obtained from the same biometric by varying the convolution kernels thus enabling the cancelability of the templates. We evaluate the proposed method using the illumination subset of the CMU pose, illumination, and expressions (PIE) face dataset. Our proposed method is very interesting from a pattern recognition theory point of view, as we are able to 'encrypt' the data and perform recognition in the encrypted domain that performs as well as the unencrypted case, regardless of the encryption kernel used; we show analytically that the recognition performance remains invariant to the proposed encryption scheme, while retaining the desired shift-invariance property of correlation filters.","PeriodicalId":335842,"journal":{"name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","volume":"197 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123014560","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}

引用次数: 311

WillHunter: interactive image retrieval with multilevel relevance 多层次关联的交互式图像检索

Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-09-20 DOI: 10.1109/ICPR.2004.1334430

Hong Wu, Hanqing Lu, Songde Ma

引用次数: 18

Bayesian face recognition using a Markov chain Monte Carlo method 贝叶斯人脸识别利用马尔科夫链蒙特卡罗方法

Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-09-20 DOI: 10.1109/ICPR.2004.1334678

A. Matsui, S. Clippingdale, Fumiki Uzawa, Takashi Matsumoto

引用次数: 14

Who are you? [face recognition] 你是谁?(人脸识别)

Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-09-20 DOI: 10.1109/ICPR.2004.1334683

M. C. Santana, E. Grosso, O. Déniz-Suárez

引用次数: 3

Region based /spl alpha/-semantics graph driven image retrieval 基于区域/spl alpha/-语义图驱动的图像检索

Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-09-20 DOI: 10.1109/ICPR.2004.1333920

Ruofei Zhang, Sandeep Khanzode, Zhongfei Zhang

{"title":"Region based /spl alpha/-semantics graph driven image retrieval","authors":"Ruofei Zhang, Sandeep Khanzode, Zhongfei Zhang","doi":"10.1109/ICPR.2004.1333920","DOIUrl":"https://doi.org/10.1109/ICPR.2004.1333920","url":null,"abstract":"This work is about content based image database retrieval, focusing on developing a classification based methodology to address semantics-intensive image retrieval. With self organization map based image feature grouping, a visual dictionary is created for color, texture, and shape feature attributes, respectively. Labeling each training image with the keywords in the visual dictionary, a classification tree is built. Based on the statistical properties of the feature space we define a structure, called /spl alpha/-semantics graph, to discover the hidden semantic relationships among the semantic repositories embodied in the image database. With the /spl alpha/-semantics graph, each semantic repository is modeled as a unique fuzzy set to explicitly address the semantic uncertainty and the semantic overlap existing among the repositories in the feature space. A retrieval algorithm combining the built classification tree with the developed fuzzy set models to deliver semantically relevant image retrieval is provided. The experimental evaluations have demonstrated that the proposed approach models the semantic relationships effectively and outperforms a state-of-the-art content based image retrieval system in the literature both in effectiveness and efficiency.","PeriodicalId":335842,"journal":{"name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130786466","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}

引用次数: 0

Efficient multimodal features for automatic soccer highlight generation 高效的多模式功能，自动足球高光生成

Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-09-20 DOI: 10.1109/ICPR.2004.1334691

K. Wan, Changsheng Xu

引用次数: 25

Gesture tracking and recognition for lecture video editing 用于演讲视频编辑的手势跟踪和识别

Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-09-20 DOI: 10.1109/ICPR.2004.1334682

Feng Wang, C. Ngo, T. Pong

引用次数: 25