发布求助
文献互助 智能选刊 最新文献

[1990] Proceedings. 10th International Conference on Pattern Recognition最新文献

筛选
英文 中文
New definition and fast recognition of digital straight segments and arcs 新的定义和快速识别数字直线段和弧
[1990] Proceedings. 10th International Conference on Pattern Recognition Pub Date : 1990-06-16 DOI: 10.1109/ICPR.1990.119324
V. Kovalevsky
{"title":"New definition and fast recognition of digital straight segments and arcs","authors":"V. Kovalevsky","doi":"10.1109/ICPR.1990.119324","DOIUrl":"https://doi.org/10.1109/ICPR.1990.119324","url":null,"abstract":"The definition and recognition algorithm for a digital straight segment (DSS) is presented. The points of a DSS must have a limited distance from that edge. A recognition algorithm is given which uses only integer arithmetic and needs an average of about 10 such operations per point. The definition of a digital circular arc (DCA) which uses the notion of centers of the pixels (a pixel is considered as an elementary rectangular area) on both sides of a given curve is given. The centers comprise two sets: the left and the right. The curve is a DCA if a Euclidean circle separating the sets from each other exists. An efficient algorithm for finding all such circles is presented.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115709376","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: 96
Industrial image processing by means of an image recognition integrated system 一种基于图像识别的工业图像处理集成系统
[1990] Proceedings. 10th International Conference on Pattern Recognition Pub Date : 1990-06-16 DOI: 10.1109/ICPR.1990.119390
Eric Persoon, Geert Nijholt, G. Maguire, John O'Brien
{"title":"Industrial image processing by means of an image recognition integrated system","authors":"Eric Persoon, Geert Nijholt, G. Maguire, John O'Brien","doi":"10.1109/ICPR.1990.119390","DOIUrl":"https://doi.org/10.1109/ICPR.1990.119390","url":null,"abstract":"An overview of the requirements for industrial applications of computer vision is given. A method called multilevel input binary template matching, which applies binary template matching to gray-level images, is presented. With this method, a vision system can be tailored to the difficulty of the individual computer-vision application while maintaining high speed and high reliability in all cases. A full custom VLSI specially designed for binary template matching is discussed. This dedicated VLSI chip, called IRIS, has a configurable kernel up to a size of 1024 elements for 1-D or up to 32*32 elements for 2-D, and has integrated line buffers. Some application examples from the field of industrial automation are presented.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123912671","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
Discrete invertible affine transformations 离散可逆仿射变换
[1990] Proceedings. 10th International Conference on Pattern Recognition Pub Date : 1990-06-16 DOI: 10.1109/ICPR.1990.119343
M. Shizawa
{"title":"Discrete invertible affine transformations","authors":"M. Shizawa","doi":"10.1109/ICPR.1990.119343","DOIUrl":"https://doi.org/10.1109/ICPR.1990.119343","url":null,"abstract":"The theory and algorithm of a general method that constructs one-to-one mappings on an n-dimensional digital lattice are presented. The mapping is constructed so that any given equivolume affine transformation can be approximated. Equivolume affine transformations include translation, reflection, and skew. It is shown that (n/sup 2/-1) fundamental skew transformations, n fundamental translations, and some reflective transformations are sufficient to represent arbitrary equivolume affine transformation. One-to-one integer approximation of the fundamental transformations and approximation error propagation rules are described. Minimum error decomposition algorithms for the equivolume affine transformation in n-dimensional space and two-dimensional space are proposed.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124173137","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
AMP: an autonomous multi-processor for image processing and computer vision AMP:用于图像处理和计算机视觉的自主多处理器
[1990] Proceedings. 10th International Conference on Pattern Recognition Pub Date : 1990-06-16 DOI: 10.1109/ICPR.1990.119409
R. Taniguchi, M. Amamiya
{"title":"AMP: an autonomous multi-processor for image processing and computer vision","authors":"R. Taniguchi, M. Amamiya","doi":"10.1109/ICPR.1990.119409","DOIUrl":"https://doi.org/10.1109/ICPR.1990.119409","url":null,"abstract":"An autonomous multiprocessor (AMP) for image processing and computer vision is presented. It provides high-performance image processing. It has many processor elements (PEs) connected to each other through a communication network. Each PE is asynchronously executed by a data flow control mechanism. It is designed on the basis of a circular pipeline architecture and has a mechanism to work like multiple logical PEs. Each pixel of an image is mapped onto one logical PE, and its data is stored in an operand memory register of a logical PE. Image data is stored distributively in the PEs of the system, and required pixel values are transferred to other PEs by inter-PE communication.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114475316","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
Some results on feature detection using residual analysis 残差分析在特征检测中的一些结果
[1990] Proceedings. 10th International Conference on Pattern Recognition Pub Date : 1990-06-16 DOI: 10.1109/ICPR.1990.118187
M.-H. Chen, D. Lee, T. Pavlidis
{"title":"Some results on feature detection using residual analysis","authors":"M.-H. Chen, D. Lee, T. Pavlidis","doi":"10.1109/ICPR.1990.118187","DOIUrl":"https://doi.org/10.1109/ICPR.1990.118187","url":null,"abstract":"Images are considered as consisting of three parts: features, noise, and smooth components. After a smoothing operation, the difference between the result and the original image has the characteristics of noise in areas away from features. Systematic trends in the difference indicate features such as edges, corners, or textures. It is shown that the autocorrelation function of the residuals takes specific forms when computed along various paths, and in particular along a circle or a disk centered at a zero crossing of residuals. Then, feature detection is reduced to classifying the autocorrelation profile. An implementation of this technique is described.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"140 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114758671","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
On local detection of moving edges 关于运动边缘的局部检测
[1990] Proceedings. 10th International Conference on Pattern Recognition Pub Date : 1990-06-16 DOI: 10.1109/ICPR.1990.118085
T. Hwang, James J. Clark
{"title":"On local detection of moving edges","authors":"T. Hwang, James J. Clark","doi":"10.1109/ICPR.1990.118085","DOIUrl":"https://doi.org/10.1109/ICPR.1990.118085","url":null,"abstract":"The authors propose a detection framework with multiple velocity channels for moving edges based on a generalization of J. Canny's edge detector (1986). Finite state machines (FSMs) are set up at discrete lattice points in the image plane and operate based on the outputs of all velocity channels. The outputs of the FSMs denote whether there are edges at their corresponding positions, and their states record the edge velocities. In the temporal dimension, statistics are attached to the edges to aid in removing phantom edges.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"67 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114528268","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
MAR: an integrated system for focal plane edge tracking with parallel analog processing and built-in primitives for image acquisition and analysis MAR:焦平面边缘跟踪的集成系统，具有并行模拟处理和用于图像采集和分析的内置原语
[1990] Proceedings. 10th International Conference on Pattern Recognition Pub Date : 1990-06-16 DOI: 10.1109/ICPR.1990.119372
M. Tremblay, D. Poussart
{"title":"MAR: an integrated system for focal plane edge tracking with parallel analog processing and built-in primitives for image acquisition and analysis","authors":"M. Tremblay, D. Poussart","doi":"10.1109/ICPR.1990.119372","DOIUrl":"https://doi.org/10.1109/ICPR.1990.119372","url":null,"abstract":"The Multiport Array Receptor (MAR), a system which combines optical sensing with integrated focal-plane processing capabilities, is described. Its central element is a photosensor array with hexagonal tesselation and complex peripheral selection logic which provides parallel analog readout over prescribed areas. An external computing module performs real-time spatial convolution at multiple resolutions while a closed-loop microprogrammed controller addresses regions of interest and supervises communication between the camera and the host computer. This integrated image sensor and processor implements programmed sequences of instruction primitives and yields a complete state description of each processed pixel. It is capable of automatic edge tracking and returns lists of connected pixels.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122003967","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
Statistical analysis of inherent ambiguities in recovering 3-D motion from a noisy flow field 从噪声流场中恢复三维运动固有模糊性的统计分析
[1990] Proceedings. 10th International Conference on Pattern Recognition Pub Date : 1990-06-16 DOI: 10.1109/ICPR.1990.118131
G. Young, R. Chellappa
{"title":"Statistical analysis of inherent ambiguities in recovering 3-D motion from a noisy flow field","authors":"G. Young, R. Chellappa","doi":"10.1109/ICPR.1990.118131","DOIUrl":"https://doi.org/10.1109/ICPR.1990.118131","url":null,"abstract":"The inherent ambiguities in recovering 3-D motion information from a single optical flow field are studied using a statistical model. These ambiguities are quantified using the Cramer-Rao lower bound, which is a lower bound for the error variances of motion parameter estimates. This performance bound is independent of the motion estimation algorithms, and can always be computed for any arbitrary 3-D motion of a rigid surface by inverting a 5*5 matrix. For the general motion of an arbitrary surface, it turns out that not every pixel gives information regarding 3-D motion estimation. It is shown that the aperture problem in computing the optical flow restricts the nontrivial information about the 3-D motion to a sparse set of pixels at which both components of the flow velocity are observable. Computer simulations are used to study the dependence of the inherent ambiguities on the underlying motion, the field of view, and the number of feature points for the motion in front of a nonplanar environment. It is shown that introducing a smoothness constraint by fitting local patches gives even lower bounds and thus is a justified technique for stabilizing the ill-posed motion estimation problem.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"377 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123957989","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: 94
Algebraic error analysis for surface curvatures of 3-D range images obtained by different methods 不同方法获得的三维距离图像曲面曲率的代数误差分析
[1990] Proceedings. 10th International Conference on Pattern Recognition Pub Date : 1990-06-16 DOI: 10.1109/ICPR.1990.118159
N. Abdelmalek
{"title":"Algebraic error analysis for surface curvatures of 3-D range images obtained by different methods","authors":"N. Abdelmalek","doi":"10.1109/ICPR.1990.118159","DOIUrl":"https://doi.org/10.1109/ICPR.1990.118159","url":null,"abstract":"Algebraic error analysis for the calculated surface curvatures of 3-D range images is presented for four curvature estimation techniques in the literature. The error analysis is used to study the experimental results obtained by P.J. Flynn and A.K. Jain (1989). It is concluded that the two methods which give better curvature estimations with comparative accuracies have almost identical curvature error bounds. The weaknesses of the other two methods are not due to large error terms in the calculated curvatures, but rather to other factors, such as inaccurate determination of the tangent planes or inaccurate estimations of the directional first- and second-order derivatives.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125820879","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
Spatio-temporal edge focusing 时空边缘聚焦
[1990] Proceedings. 10th International Conference on Pattern Recognition Pub Date : 1990-06-16 DOI: 10.1109/ICPR.1990.118095
E. Z. Tihanyi, J. Barron
{"title":"Spatio-temporal edge focusing","authors":"E. Z. Tihanyi, J. Barron","doi":"10.1109/ICPR.1990.118095","DOIUrl":"https://doi.org/10.1109/ICPR.1990.118095","url":null,"abstract":"An automated edge detection algorithm, referred to as spatio-temporal edge focusing, is presented. It combines spatial edge focusing and temporal edge focusing. While spatial edge focusing and temporal edge focusing each have their own advantages and disadvantages, it is shown that the combination of these two techniques maintains their advantages while minimizing or removing most of their disadvantages. The final result is an automated edge detection algorithm that produces relatively noise-free edge maps with well-localized edges.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124822967","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
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