发布求助
文献互助 智能选刊 最新文献

Proceedings of 13th International Conference on Pattern Recognition最新文献

筛选
英文 中文
Feature extraction from aerial images and structural stereo matching 航空影像特征提取与结构立体匹配
Proceedings of 13th International Conference on Pattern Recognition Pub Date : 1996-08-25 DOI: 10.1109/ICPR.1996.547294
D. Torkar, N. Pavesic
{"title":"Feature extraction from aerial images and structural stereo matching","authors":"D. Torkar, N. Pavesic","doi":"10.1109/ICPR.1996.547294","DOIUrl":"https://doi.org/10.1109/ICPR.1996.547294","url":null,"abstract":"In this paper, a method of generating structural descriptions of stereo image pairs and their matching to recover 3D form of objects in space, is discussed. The method consists of the following steps: 1) straight line segments are extracted in both images and the relational among them are investigated; and 2) the relational subgraphs are constructed and the correspondence graph is created. Using the \"stable marriage\" searching algorithm the features in one image corresponding to features in the other image are found. The method was tested on a set of aerial stereo images of urban scenes.","PeriodicalId":290297,"journal":{"name":"Proceedings of 13th International Conference on Pattern Recognition","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126121710","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: 7
Real-time object tracking by rotating range sensor 基于旋转距离传感器的实时目标跟踪
Proceedings of 13th International Conference on Pattern Recognition Pub Date : 1996-08-25 DOI: 10.1109/ICPR.1996.546139
S. Hiura, A. Yamaguchi, Kosuke Sato, S. Inokuchi
{"title":"Real-time object tracking by rotating range sensor","authors":"S. Hiura, A. Yamaguchi, Kosuke Sato, S. Inokuchi","doi":"10.1109/ICPR.1996.546139","DOIUrl":"https://doi.org/10.1109/ICPR.1996.546139","url":null,"abstract":"We propose a new method to track 3-D motion of an object in real-time, using range images. A very high speed range sensor \"Silicon Range Finder\" makes it possible to acquire range images at more than 30 frames per second, and rotated to keep the object in the measurable area. Rough but fast results of range image processing controls the angle of the range sensor, and the object centered range images decide the pose of the object. The 3-D CG rendering hardware of the graphics workstation generates range images from the surface model very fast, so it makes the comparison algorithm simple. Tracking speed and accuracies of estimated motion seem to be feasible for the man-machine cooperative systems.","PeriodicalId":290297,"journal":{"name":"Proceedings of 13th International Conference on Pattern Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129388101","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
Color-sensitive biosensors for imaging 用于成像的色敏生物传感器
Proceedings of 13th International Conference on Pattern Recognition Pub Date : 1996-08-25 DOI: 10.1109/ICPR.1996.546965
P. Silfsten, S. Parkkinen, J. Luostarinen, A. Khodonov, T. Jääskeläinen, J. Parkkinen
{"title":"Color-sensitive biosensors for imaging","authors":"P. Silfsten, S. Parkkinen, J. Luostarinen, A. Khodonov, T. Jääskeläinen, J. Parkkinen","doi":"10.1109/ICPR.1996.546965","DOIUrl":"https://doi.org/10.1109/ICPR.1996.546965","url":null,"abstract":"Research on an artificial retina is mainly concentrated on the design of silicon based integrated circuits, where the spatial structure of the circuit and the electrical design of a pixel plays the main role. Color sensitivity has not been an issue, or it is realized by using separate filters in front of the circuit. There are only few studies concerning an artificial retina based on a biomolecular structure. In this study we describe some optically active biomolecules, which are potential materials for construction of an artificial retina. We use bacteriorhodopsin and its variants. This protein is produced by a bacterium, Halobacterium salinarium. The protein is closely related to the light sensitive molecule of human retina. The studied molecules have different wavelength properties with each other and when mounted on a polyvinylalcohol film, they produce an electric signal from optical input. We have produced a set of protein films with different wavelength properties and we report the basic characteristics of these films, referring them as basic elements of an artificial retina. The design principles of a biomolecule based artificial retina is also discussed.","PeriodicalId":290297,"journal":{"name":"Proceedings of 13th International Conference on Pattern Recognition","volume":"15 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129392156","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
A knowledge acquisition technique for recognizing handprinted Chinese characters 一种手印汉字识别的知识获取技术
Proceedings of 13th International Conference on Pattern Recognition Pub Date : 1996-08-25 DOI: 10.1109/ICPR.1996.546949
A. Amin, Michael Bemford, A. Hoffmann, Ashesh Mahidadia, P. Compton
{"title":"A knowledge acquisition technique for recognizing handprinted Chinese characters","authors":"A. Amin, Michael Bemford, A. Hoffmann, Ashesh Mahidadia, P. Compton","doi":"10.1109/ICPR.1996.546949","DOIUrl":"https://doi.org/10.1109/ICPR.1996.546949","url":null,"abstract":"This paper presents a new approach to building classifiers for Chinese character recognition. A new knowledge acquisition technique is used for building incrementally a knowledge based system for the classification task. The new knowledge acquisition technique is based on ripple down rules, which is an effective method for building large knowledge bases. We extended ripple down rules to be able to acquire graphical knowledge. In this paper a Hough transform technique is used for extracting the features which are being used for a knowledge based system. A prototype has been implemented and initial experimental results are promising.","PeriodicalId":290297,"journal":{"name":"Proceedings of 13th International Conference on Pattern Recognition","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128388899","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: 4
Structural compression for document analysis 结构压缩文件分析
Proceedings of 13th International Conference on Pattern Recognition Pub Date : 1996-08-25 DOI: 10.1109/ICPR.1996.547029
O. Kia, D. Doermann
{"title":"Structural compression for document analysis","authors":"O. Kia, D. Doermann","doi":"10.1109/ICPR.1996.547029","DOIUrl":"https://doi.org/10.1109/ICPR.1996.547029","url":null,"abstract":"In this paper we describe a structural compression technique to be used for document text image storage and retrieval. The primary objective is to provide an efficient representation, storage, transmission and display. A secondary objective is to provide an encoding which allows access to specified regions within the image and facilitates traditional document processing operations without requiring complete decoding. We describe an algorithm which symbolically decomposes a document image and structurally orders the error bitmap based on a probabilistic model. The resultant symbol and error representations lend themselves to reasonably high compression ratios and are structured so as to allow operations directly on the compressed image. The compression scheme is implemented and compared to traditional compression methods.","PeriodicalId":290297,"journal":{"name":"Proceedings of 13th International Conference on Pattern Recognition","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128489742","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
Effect of time-spatial size of motion image for localization by using the spotting method 运动图像的时空大小对点状法定位的影响
Proceedings of 13th International Conference on Pattern Recognition Pub Date : 1996-08-25 DOI: 10.1109/ICPR.1996.546017
T. Nishimura, H. Kojima, Y. Itoh, A. Held, S. Nozaki, S. Nagaya, R. Oka
{"title":"Effect of time-spatial size of motion image for localization by using the spotting method","authors":"T. Nishimura, H. Kojima, Y. Itoh, A. Held, S. Nozaki, S. Nagaya, R. Oka","doi":"10.1109/ICPR.1996.546017","DOIUrl":"https://doi.org/10.1109/ICPR.1996.546017","url":null,"abstract":"We have been developing a localization method for an autonomous robot without using any prior knowledge or assumptions about the environment. The method is general and robust and can be used in real world robot tasks. With a map description based on a reduced image sequence, we detect a frame sequence in the map which matches an input frame sequence, by means of reference interval-free continuous dynamic programming (RIFCDP). The method can cope with changes in the robot's speed because RIFCDP can spot arbitrary frame sequences by nonlinear matching. In this paper, we show a real-time localization system, and we illustrate the effectiveness of our method in the real world by some evaluation experiments.","PeriodicalId":290297,"journal":{"name":"Proceedings of 13th International Conference on Pattern Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128752895","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: 7
Real-time self-calibrating stereo person tracking using 3-D shape estimation from blob features 基于blob特征的三维形状估计的实时自校准立体人物跟踪
Proceedings of 13th International Conference on Pattern Recognition Pub Date : 1996-08-25 DOI: 10.1109/ICPR.1996.547022
A. Azarbayejani, A. Pentland
{"title":"Real-time self-calibrating stereo person tracking using 3-D shape estimation from blob features","authors":"A. Azarbayejani, A. Pentland","doi":"10.1109/ICPR.1996.547022","DOIUrl":"https://doi.org/10.1109/ICPR.1996.547022","url":null,"abstract":"We describe a method for estimation of 3D geometry from 2D blob features. Blob features are clusters of similar pixels in the image plane and can arise from similarity of color, texture, motion and other signal-based metrics. The motivation for considering such features comes from recent successes in real-time extraction and tracking of such blob features in complex cluttered scenes in which traditional feature finders fail, e.g. scenes containing moving people. We use nonlinear modeling and a combination of iterative and recursive estimation methods to recover 3D geometry from blob correspondences across multiple images. The 3D geometry includes the 3D shapes, translations, and orientations of blobs and the relative orientation of the cameras. Using this technique, we have developed a real-time wide-baseline stereo person tracking system which can self-calibrate itself from watching a moving person and can subsequently track people's head and hands with RIMS errors of 1-2 cm in translation and 2 degrees in rotation. The blob formulation is efficient and reliable, running at 20-30 Hz on a pair of SGI Indy R4400 workstations with no special hardware.","PeriodicalId":290297,"journal":{"name":"Proceedings of 13th International Conference on Pattern Recognition","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129655420","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: 185
Automated detection of human for visual surveillance system 人的自动检测用于视觉监控系统
Proceedings of 13th International Conference on Pattern Recognition Pub Date : 1996-08-25 DOI: 10.1109/ICPR.1996.547291
Y. Kuno, Nakayama Watanabe, Y. Shimosakoda, Satoshi Nakagawa
{"title":"Automated detection of human for visual surveillance system","authors":"Y. Kuno, Nakayama Watanabe, Y. Shimosakoda, Satoshi Nakagawa","doi":"10.1109/ICPR.1996.547291","DOIUrl":"https://doi.org/10.1109/ICPR.1996.547291","url":null,"abstract":"This paper describes a robust and reliable method of human detection for visual surveillance systems. The merit of this method is to use simple shape parameters of silhouette patterns to classify humans from other moving objects such as butterflies and autonomous factory vehicles. An extra function based on the brightness level transformation is used to extract the precise shape of the silhouette patterns. An approach to overcome the occlusions of humans is also proposed. We tested our method for 2,500 images (1,100 from humans and 1,400 from other moving objects). Our test system detected the humans at the rate of 98% (=1,077/1,100) and judged 92% (=1,283/1,400) of the other moving objects as non-humans.","PeriodicalId":290297,"journal":{"name":"Proceedings of 13th International Conference on Pattern Recognition","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127105668","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: 120
A prototype system for interpreting hand-sketched floor plans 解释手绘平面图的原型系统
Proceedings of 13th International Conference on Pattern Recognition Pub Date : 1996-08-25 DOI: 10.1109/ICPR.1996.547268
Yasuhiro Aoki, Akio Shio, Hiroyuki Arai, Kazumi Odaka
{"title":"A prototype system for interpreting hand-sketched floor plans","authors":"Yasuhiro Aoki, Akio Shio, Hiroyuki Arai, Kazumi Odaka","doi":"10.1109/ICPR.1996.547268","DOIUrl":"https://doi.org/10.1109/ICPR.1996.547268","url":null,"abstract":"A prototype system for drawing interpretation that automatically converts hand-sketched floor-plans into the CAD format is presented. The main problems in interpreting hand-sketched drawings are positional ambiguity and shape distortion. In the proposed method, positional ambiguity is able to be corrected in a nearest grid-location manner because floor-plan elements are normally drawn on/along grid lines that correspond to the modular proportions. Shape distortion is able to be corrected by template-matching of closed regions because architectural elements mostly consist of one or more closed regions of basic figures: triangles, squares, circles, and so on. The system was tested using 150 floor-plan drawings hand-sketched by three subjects without the use of rulers or templates. The results showed that sufficient recognition performance for practical use was able to be obtained.","PeriodicalId":290297,"journal":{"name":"Proceedings of 13th International Conference on Pattern Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127403293","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: 6
An MRF model-based method for unsupervised textured image segmentation 一种基于MRF模型的无监督纹理图像分割方法
Proceedings of 13th International Conference on Pattern Recognition Pub Date : 1996-08-25 DOI: 10.1109/ICPR.1996.546926
H. Noda, M. N. Shirazi, E. Kawaguchi
{"title":"An MRF model-based method for unsupervised textured image segmentation","authors":"H. Noda, M. N. Shirazi, E. Kawaguchi","doi":"10.1109/ICPR.1996.546926","DOIUrl":"https://doi.org/10.1109/ICPR.1996.546926","url":null,"abstract":"This paper proposes a Markov random field (MRF) model-based method for unsupervised segmentation of images consisting of multiple textures. This method uses a hierarchical MRF with two layers, the first layer representing an unobservable region image and the second layer representing multiple textures which cover each region. This method is an iterative method based on the framework of the expectation and maximization (EM) method. We make use of an approximation for the Baum function in the expectation step. This reduces the parameter estimation to the maximum likelihood (ML) estimation given the current estimate of the region image. An estimation of the region image (image segmentation) is carried out by a deterministic relaxation method proposed by us.","PeriodicalId":290297,"journal":{"name":"Proceedings of 13th International Conference on Pattern Recognition","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127504204","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: 5
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：604180095
Book学术官方微信