发布求助
文献互助 智能选刊 最新文献

18th International Conference on Pattern Recognition (ICPR'06)最新文献

筛选
英文 中文
Fingerprint Retrieval by Complex Filter Responses 基于复杂滤波响应的指纹检索
18th International Conference on Pattern Recognition (ICPR'06) Pub Date : 2006-08-20 DOI: 10.1109/ICPR.2006.577
Manhua Liu, Xudong Jiang, A. Kot
{"title":"Fingerprint Retrieval by Complex Filter Responses","authors":"Manhua Liu, Xudong Jiang, A. Kot","doi":"10.1109/ICPR.2006.577","DOIUrl":"https://doi.org/10.1109/ICPR.2006.577","url":null,"abstract":"This paper proposes an approach of fingerprint retrieval based on the continuous classification of two complex filter responses. Two complex filters are introduced and applied on the fingerprint orientation field to extract the local singularities, the similarities to the singular points. A numerical feature vector from the aligned fingerprint local singularities is constructed as the global feature for fingerprint retrieval. The continuous classification is employed to retrieve a subset of fingerprints similar to the query fingerprint for the finer matching. Experimental results on NIST fingerprint database 4 (NIST-4) shows the effectiveness of the proposed fingerprint retrieval approach","PeriodicalId":236033,"journal":{"name":"18th International Conference on Pattern Recognition (ICPR'06)","volume":"46 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":"122676815","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: 39
A Markovian Approach for Handwritten Document Segmentation 一种手写文档分割的马尔可夫方法
18th International Conference on Pattern Recognition (ICPR'06) Pub Date : 2006-08-20 DOI: 10.1109/ICPR.2006.94
Stéphane Nicolas, T. Paquet, L. Heutte
{"title":"A Markovian Approach for Handwritten Document Segmentation","authors":"Stéphane Nicolas, T. Paquet, L. Heutte","doi":"10.1109/ICPR.2006.94","DOIUrl":"https://doi.org/10.1109/ICPR.2006.94","url":null,"abstract":"We address in this paper the problem of segmenting complex handwritten pages such as novelist drafts or authorial manuscripts. We propose to use stochastic and contextual models in order to cope with local spatial variability, and to take into account some prior knowledge about the global structure of the document image. The models we propose to use are Markov random field models","PeriodicalId":236033,"journal":{"name":"18th International Conference on Pattern Recognition (ICPR'06)","volume":"70 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":"122513722","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
Neighbor Pixel Mixture 邻居像素混合
18th International Conference on Pattern Recognition (ICPR'06) Pub Date : 2006-08-20 DOI: 10.1109/ICPR.2006.852
Masayuki Tanaka, M. Okutomi
{"title":"Neighbor Pixel Mixture","authors":"Masayuki Tanaka, M. Okutomi","doi":"10.1109/ICPR.2006.852","DOIUrl":"https://doi.org/10.1109/ICPR.2006.852","url":null,"abstract":"Pixel mixture is a technique to reduce the read-out time of an image by mixing multiple pixel values on an imager. Ordinary pixel mixtures mix the values of equicolor pixels. However, the equicolor pixels are not contiguous on the Bayer pattern. Mixing non-contiguous pixels degrades the resolution of the mixed image. This paper proposes a novel pixel mixture method which we call a \"neighbor pixel mixture\". The resolution of the neighbor pixel mixture image is superior to that of existing pixel mixtures. The proposed method mixes the values of the neighbor pixels with different colors. In the proposed method, a weighted average is used for the mixing operation, whereas ordinary pixel mixtures apply a simple average. We also discuss a guideline to design weights for averaging","PeriodicalId":236033,"journal":{"name":"18th International Conference on Pattern Recognition (ICPR'06)","volume":"24 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":"122545528","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
Object Contour Detection Using Spatio-temporal Self-sim 基于时空自模拟的目标轮廓检测
18th International Conference on Pattern Recognition (ICPR'06) Pub Date : 2006-08-20 DOI: 10.1109/ICPR.2006.875
H. Takeshima, T. Ida, Toshimitsu Kaneko
{"title":"Object Contour Detection Using Spatio-temporal Self-sim","authors":"H. Takeshima, T. Ida, Toshimitsu Kaneko","doi":"10.1109/ICPR.2006.875","DOIUrl":"https://doi.org/10.1109/ICPR.2006.875","url":null,"abstract":"A novel contour detector that refines a rough boundary between an object and a background to a precise boundary in moving pictures robustly is proposed. To estimate boundaries of objects, the proposed method uses self-similar block matching (SSBM) in spatio-temporal 3-D space. SSBM, which searches a larger similar block for each block placed near a boundary, estimates contours correctly. In this paper, it is shown analytically that the robustness of spatio-temporal SSBM is superior to that of conventional 2-D SSBM. Since SSBM does not assume contour smoothness, the proposed algorithm can detect sharp corners more accurately than the methods using smooth constraints such as Snake. Experimental results show that the proposed method is effective for estimating precise regions of objects even if pictures are noisy","PeriodicalId":236033,"journal":{"name":"18th International Conference on Pattern Recognition (ICPR'06)","volume":"6 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":"122589815","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
Fingerprint Matching Using Minutia Polygons 使用精细多边形的指纹匹配
18th International Conference on Pattern Recognition (ICPR'06) Pub Date : 2006-08-20 DOI: 10.1109/ICPR.2006.571
Xuefeng Liang, Tetsuo Asano
{"title":"Fingerprint Matching Using Minutia Polygons","authors":"Xuefeng Liang, Tetsuo Asano","doi":"10.1109/ICPR.2006.571","DOIUrl":"https://doi.org/10.1109/ICPR.2006.571","url":null,"abstract":"Fingerprint distortion changes both the geometric position and orientation of minutiae, and leads to difficulties in establishing a match among multiple impressions acquired from the same finger In this paper, minutia polygons are used to match distorted fingerprints. A minutia polygon describes not only the minutia type and orientation but also the minutia shape. This allows the minutia polygon to be bigger than the conventional tolerance box without losing matching accuracy. In other words, a minutia polygon has a higher ability to tolerate distortion. Furthermore, the proposed matching method employs an improved distortion model using a multi-quadric basis function with parameters. Adjustable parameters make this model more suitable for fingerprint distortion. Experimental results show the proposed method is two times faster and more accurate (especially, on fingerprints with heavy distortion) than the method by A.M.Bazen and S.H.Gerez (2003)","PeriodicalId":236033,"journal":{"name":"18th International Conference on Pattern Recognition (ICPR'06)","volume":"63 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":"122635633","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
Automatic Pose Recovery for High-Quality Textures Generation 自动姿态恢复为高质量的纹理生成
18th International Conference on Pattern Recognition (ICPR'06) Pub Date : 2006-08-20 DOI: 10.1109/ICPR.2006.303
Jinhui Hu, Suya You, U. Neumann
{"title":"Automatic Pose Recovery for High-Quality Textures Generation","authors":"Jinhui Hu, Suya You, U. Neumann","doi":"10.1109/ICPR.2006.303","DOIUrl":"https://doi.org/10.1109/ICPR.2006.303","url":null,"abstract":"This paper proposes new techniques to generate high quality textures for urban building models by automatic camera calibration and pose recovery. The camera pose is decomposed into an orientation and a translation, an edge error model and knowledge-based filters are used to estimate correct vanishing points with heavy trees occlusion, and the vanishing points are used for the camera calibration and orientation estimation. We propose new techniques to estimate the camera orientation with infinite vanishing points and translation with under-constraints. The final textures are generated using color calibration and blending with the recovered pose. A number of textures for outdoor buildings are automatically generated, which shows the effectiveness of our algorithms","PeriodicalId":236033,"journal":{"name":"18th International Conference on Pattern Recognition (ICPR'06)","volume":"42 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":"122647140","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: 11
Multimodal Registration using the Discrete Wavelet Frame Transform 离散小波框架变换的多模态配准
18th International Conference on Pattern Recognition (ICPR'06) Pub Date : 2006-08-20 DOI: 10.1109/ICPR.2006.839
Shutao Li, Jinglin Peng, J. Kwok, Jing Zhang
{"title":"Multimodal Registration using the Discrete Wavelet Frame Transform","authors":"Shutao Li, Jinglin Peng, J. Kwok, Jing Zhang","doi":"10.1109/ICPR.2006.839","DOIUrl":"https://doi.org/10.1109/ICPR.2006.839","url":null,"abstract":"Image registration is a critical step in medical image analysis. In this paper, a novel image registration method based on the discrete wavelet frame transform (DWFT) and the sum of absolute distance (SAD) method is proposed. First, the multimodal images are decomposed by DWFT, which is shift-invariant compared to traditional dyadic wavelet transforms. Then the energy maps are computed from the details sub-band images. Finally, genetic algorithm (GA) is adopted to obtain the minimum SAD between the two energy maps. The proposed method is tested on 50 pairs of two-dimensional T1-weighted and T2-weighted modal images. Experimental results demonstrated that the proposed method can achieve high accuracy in the rigid transformation case","PeriodicalId":236033,"journal":{"name":"18th International Conference on Pattern Recognition (ICPR'06)","volume":"7 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":"114281213","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: 12
GMM-based SVM for face recognition 基于gmm的SVM人脸识别
18th International Conference on Pattern Recognition (ICPR'06) Pub Date : 2006-08-20 DOI: 10.1109/ICPR.2006.611
H. Bredin, N. Dehak, G. Chollet
{"title":"GMM-based SVM for face recognition","authors":"H. Bredin, N. Dehak, G. Chollet","doi":"10.1109/ICPR.2006.611","DOIUrl":"https://doi.org/10.1109/ICPR.2006.611","url":null,"abstract":"A new face recognition algorithm is presented. It supposes that a video sequence of a person is available both at enrollment and test time. During enrollment, a client Gaussian mixture model (GMM) is adapted from a world GMM using eigenface features extracted from each frame of the video. Then, a support vector machine (SVM) is used to find a decision border between the client GMM and pseudo-impostors GMMs. At test time, a GMM is adapted from the test video and a decision is taken using the previously learned client SVM. This algorithm brings a 3.5% equal error rate (EER) improvement over the biosecure reference system on the Pooled protocol of the BANCA database","PeriodicalId":236033,"journal":{"name":"18th International Conference on Pattern Recognition (ICPR'06)","volume":"41 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":"114301914","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: 28
A Complete and Rapid Feature Extraction Method for Face Recognition 一种完整快速的人脸识别特征提取方法
18th International Conference on Pattern Recognition (ICPR'06) Pub Date : 2006-08-20 DOI: 10.1109/ICPR.2006.53
Yu-Jie Zheng, Jing-yu Yang, Jian Yang, Xiaojun Wu, Dongjun Yu
{"title":"A Complete and Rapid Feature Extraction Method for Face Recognition","authors":"Yu-Jie Zheng, Jing-yu Yang, Jian Yang, Xiaojun Wu, Dongjun Yu","doi":"10.1109/ICPR.2006.53","DOIUrl":"https://doi.org/10.1109/ICPR.2006.53","url":null,"abstract":"Feature extraction is one of the key steps in face recognition. In this paper, common vector is used to extract features from null space of within-class scatter matrix, which is independent of the sample index in the same class and accelerates the speed of feature extraction. Furthermore, effective features in regular space are extracted to enhance the performance of face recognition. The proposed method not only solves the small sample size problem, but also extracts more effective features from face images. Experimental results on two popular databases demonstrate the effectiveness of the proposed method","PeriodicalId":236033,"journal":{"name":"18th International Conference on Pattern Recognition (ICPR'06)","volume":"20 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":"122056247","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: 3
Automatic Acquisition of Context Models and its Application to Video Surveillance 上下文模型的自动获取及其在视频监控中的应用
18th International Conference on Pattern Recognition (ICPR'06) Pub Date : 2006-08-20 DOI: 10.1109/ICPR.2006.292
Oliver Brdiczka, P. Yuen, Sofia Zaidenberg, P. Reignier, J. Crowley
{"title":"Automatic Acquisition of Context Models and its Application to Video Surveillance","authors":"Oliver Brdiczka, P. Yuen, Sofia Zaidenberg, P. Reignier, J. Crowley","doi":"10.1109/ICPR.2006.292","DOIUrl":"https://doi.org/10.1109/ICPR.2006.292","url":null,"abstract":"This paper addresses the problem of automatically acquiring context models from data. Context and human behavior are represented using a state model, called situation model. This model consists of different layers referring to entities, filters, roles, relations, situation and situation relationship. We propose a framework for the automatic acquisition of these different layers. In particular, this paper proposes a novel generic situation acquisition algorithm. The algorithm is also successfully applied to a video surveillance task and is evaluated by the public CAVIAR video database. The results are encouraging","PeriodicalId":236033,"journal":{"name":"18th International Conference on Pattern Recognition (ICPR'06)","volume":"1 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":"116978667","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: 31
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信