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
The primary raster: a multiresolution image description 主栅格:多分辨率图像描述
[1990] Proceedings. 10th International Conference on Pattern Recognition Pub Date : 1990-06-16 DOI: 10.1109/ICPR.1990.118238
V. Lacroix
{"title":"The primary raster: a multiresolution image description","authors":"V. Lacroix","doi":"10.1109/ICPR.1990.118238","DOIUrl":"https://doi.org/10.1109/ICPR.1990.118238","url":null,"abstract":"The primary raster is a multiresolution image description. This description has the form of a raster where each pixel (edgel) has four characteristics: the detection scale, the blurring scale, the local contrast, and an edgel type. The detection scale is the finest resolution where the edgel appears, while the blurring scale is the coarsest resolution where the edgel is still present. The local contrast is the difference of the mean intensities taken from each side of the edgel. The edgel type depends on the evolution of the gradient from the finest to the coarsest resolution. Experimental results on the primary raster are presented. It is concluded that the primary raster provides a basis for a higher-level image description.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"7 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":"132217839","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: 38
The design of a nonparametric hierarchical classifier 非参数分层分类器的设计
[1990] Proceedings. 10th International Conference on Pattern Recognition Pub Date : 1990-06-16 DOI: 10.1109/ICPR.1990.118140
Chea-Tin Tseng, B. Moret
{"title":"The design of a nonparametric hierarchical classifier","authors":"Chea-Tin Tseng, B. Moret","doi":"10.1109/ICPR.1990.118140","DOIUrl":"https://doi.org/10.1109/ICPR.1990.118140","url":null,"abstract":"The authors propose a method based on kernel density estimates to partition sequentially the feature space along the best feature axis (either one of the original axes or one obtained by a carefully developed one-dimensional linear feature transformation). This method alleviates the storage and classification speed problems of traditional kernel-based classifiers without losing their flexibility and their relative insensitivity to dimensionality. The authors present a simple procedure and a distribution-free criterion for finding a good smoothing parameter for the kernel density estimate and develop a one-dimensional feature linear transformation based on correlation between density functions, which can be applied regardless of the geometrical structure of the data. The authors' proposals are validated by theoretical results and by simulations. An application to the severely under-sampled problem of texture classification (only 32 design samples per class in 22-dimensional space) is presented.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"133 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":"132222919","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: 2
Computing characteristic views of quadric-surfaced solids 计算二次曲面固体的特征视图
[1990] Proceedings. 10th International Conference on Pattern Recognition Pub Date : 1990-06-16 DOI: 10.1109/ICPR.1990.118068
S. Chen, H. Freeman
{"title":"Computing characteristic views of quadric-surfaced solids","authors":"S. Chen, H. Freeman","doi":"10.1109/ICPR.1990.118068","DOIUrl":"https://doi.org/10.1109/ICPR.1990.118068","url":null,"abstract":"An algorithm is presented for computing the characteristic views (CVs) of quadric-surfaced solids. The CVs are determined by analyzing the characteristic-view domains of the object by relating changes in the topology of the object's line structure to changes in the occlusion of 3D edges. The main task of the algorithm is to compute the envelope boundaries for viewpoint regions for which the object's visible-line projections have topologically equivalent line-junction graphs. By using the concepts of generalized edge, generalized face, and generalized vertex and using the techniques of order-of-visibility propagation and edge classification, the algorithm can efficiently compute both local and global visibility of edge segments, and therefrom compute the required envelope boundaries. This algorithm is shown to hold for quadric-surfaced solids in general and to treat a polyhedral object as a special case.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"1 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":"132381381","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: 19
Connection machine vision-Replicated data structures 连接机器视觉复制数据结构
[1990] Proceedings. 10th International Conference on Pattern Recognition Pub Date : 1990-06-16 DOI: 10.1109/ICPR.1990.119373
L. Davis, L. T. Chen, P. Narayanan
{"title":"Connection machine vision-Replicated data structures","authors":"L. Davis, L. T. Chen, P. Narayanan","doi":"10.1109/ICPR.1990.119373","DOIUrl":"https://doi.org/10.1109/ICPR.1990.119373","url":null,"abstract":"The problem of efficiently processing small data structures on massively parallel single-instruction multiple-data machines using replication methods is discussed. The problem stems from considerations of both multiresolution vision systems and focus of attention vision systems. A general framework for developing replicated algorithms, based on the four steps of embedding, distribution, decomposition, and collection, is described. A simple example is provided based on computing the histogram of a gray-level image. Replicated chain processing is discussed, and an efficient algorithm for ranking the elements in a chain in log (n) time on a concurrent write parallel random access machine is presented.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"4 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":"134270159","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: 2
3D edge detection by separable recursive filtering and edge closing 基于可分递归滤波和边缘闭合的三维边缘检测
[1990] Proceedings. 10th International Conference on Pattern Recognition Pub Date : 1990-06-16 DOI: 10.1109/ICPR.1990.118182
O. Monga, R. Deriche, G. Malandain, J. Cocquerez
{"title":"3D edge detection by separable recursive filtering and edge closing","authors":"O. Monga, R. Deriche, G. Malandain, J. Cocquerez","doi":"10.1109/ICPR.1990.118182","DOIUrl":"https://doi.org/10.1109/ICPR.1990.118182","url":null,"abstract":"Edge detection in 3D images such as scanner, magnetic resonance, or spatiotemporal data is considered. A two-stage scheme based on separable recursive filtering and edge tracking/closing is proposed. The key point of the filtering stage is to use optimal recursive and separable filters to approximate gradient or Laplacian methods. The recursive nature of the operators enables one to implement infinite 3D impulse response with a computing time roughly similar to a 3*3*3 convolution mask. The principle of the edge tracking/closing is to select from the previous stage only the more reliable edge points and then to apply an edge closing method derived from the idea developed by R. Deriche and J.P. Cocquerez (1988). This makes it possible to substantially improve the results provided by the filtering stage.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"74 26 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":"132639654","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: 17
Measuring image structures using a multiscale orientation field 使用多尺度取向场测量图像结构
[1990] Proceedings. 10th International Conference on Pattern Recognition Pub Date : 1990-06-16 DOI: 10.1109/ICPR.1990.118202
J. Coggins
{"title":"Measuring image structures using a multiscale orientation field","authors":"J. Coggins","doi":"10.1109/ICPR.1990.118202","DOIUrl":"https://doi.org/10.1109/ICPR.1990.118202","url":null,"abstract":"A novel method for representing image orientation structure is used to measure the orientations of line segments in a series of increasingly blurred images. An algorithm for mapping filtered image data into an orientation feature space is defined. The algorithm is applied using four sets of filters. The results show that the algorithm effectively exploits redundancy in the feature values to yield robust inferences across a broad range of scales and through large amounts of blurring.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"47 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":"132641850","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: 2
A new method for estimation of hidden Markov model parameters 一种估计隐马尔可夫模型参数的新方法
[1990] Proceedings. 10th International Conference on Pattern Recognition Pub Date : 1990-06-16 DOI: 10.1109/ICPR.1990.119323
Y. Gao, Y. Chen, Taiyi Huang
{"title":"A new method for estimation of hidden Markov model parameters","authors":"Y. Gao, Y. Chen, Taiyi Huang","doi":"10.1109/ICPR.1990.119323","DOIUrl":"https://doi.org/10.1109/ICPR.1990.119323","url":null,"abstract":"An algorithm for estimating the parameters of a hidden Markov model (HMM) is presented. In this algorithm, the rule of parameter estimation is used to maximize the recognition accuracy or to minimize the probability of error of the recognizer which is based on hidden Markov models instead of maximizing the likelihood function in maximum likelihood estimates (MLEs). The performance of minimum probability error (MPE) estimates is better than that of MLEs. Since MPE is much more complex in computation than an MLE, a simplified implementation of MPE which is much more moderate in computation is given. Experiments on speech recognition based on HMMs show that the accuracy of the recognizer trained by the estimation method has about a 5% improvement over the MLE.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"29 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":"133611960","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: 2
An object recognition system using stochastic knowledge source and VLSI parallel architecture 基于随机知识源和VLSI并行结构的目标识别系统
[1990] Proceedings. 10th International Conference on Pattern Recognition Pub Date : 1990-06-16 DOI: 10.1109/ICPR.1990.118225
W. Mao, S. Kung
{"title":"An object recognition system using stochastic knowledge source and VLSI parallel architecture","authors":"W. Mao, S. Kung","doi":"10.1109/ICPR.1990.118225","DOIUrl":"https://doi.org/10.1109/ICPR.1990.118225","url":null,"abstract":"The authors present a system for 2D shape recognition using hidden Markov model (HMM) knowledge sources. The shape is represented by a sequence of curvature values. A ring hidden Markov model (RHMM), which incorporates a ring structure and local connectivity, is proposed. The approach solves both the context sensitivity problem and the pattern instantiation problem. Simulation results on aircraft indicate that the proposed system can achieve almost 100% recognition accuracy at a very fast learning speed. It is shown that the RHMM system can be efficiently implemented in a systolic array, permitting real-time processing.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"51 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132285742","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: 9
Optimal image algorithms on an orthogonally-connected memory-based architecture 基于正交连接存储器架构的最优图像算法
[1990] Proceedings. 10th International Conference on Pattern Recognition Pub Date : 1990-06-16 DOI: 10.1109/ICPR.1990.119381
H. Alnuweiri, V. Prasanna
{"title":"Optimal image algorithms on an orthogonally-connected memory-based architecture","authors":"H. Alnuweiri, V. Prasanna","doi":"10.1109/ICPR.1990.119381","DOIUrl":"https://doi.org/10.1109/ICPR.1990.119381","url":null,"abstract":"Processor-time optimal algorithms are presented for several image and vision problems. A parallel architecture which combines an orthogonally accessed memory with a linear array structure is used. The organization has p processors and a memory of size O(n/sup 2/) locations. The number of processors p can vary over the range (1,n/sup 3/2/) while providing optimal speedup for several problems in image analysis and vision. Such problems include labeling connected regions, computing minimum convex containers of regions, and computing nearest neighbors of pixels and regions. Optimal algorithms are presented for histogramming and computing the Hough transform. Such problems arise in medium-level vision and require global operations or dense data movement. It is shown that for these types of problems, the proposed organization is superior to the mesh and pyramid organizations.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"1 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":"127411851","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: 2
Detecting wheels of vehicle in stereo images 在立体图像中检测车辆车轮
[1990] Proceedings. 10th International Conference on Pattern Recognition Pub Date : 1990-06-16 DOI: 10.1109/ICPR.1990.118108
M. K. Leung, Thomas S. Huang
{"title":"Detecting wheels of vehicle in stereo images","authors":"M. K. Leung, Thomas S. Huang","doi":"10.1109/ICPR.1990.118108","DOIUrl":"https://doi.org/10.1109/ICPR.1990.118108","url":null,"abstract":"A method for detecting the wheels of a vehicle in stereo image pairs is presented. The method consists of two steps: geometrical transformation and circle extraction. The geometrical transformation uses the disparity values obtained from a stereo image pair to calculate the parameters of the plane containing wheels of the vehicle. These parameters are used to transform any elliptical wheels contained in the plane to circular ones which can be extracted by the circle extraction algorithm. The circle extraction algorithm consists of template matching and the Hough transform. In order to save computation and improve the results in the Hough transform, two constraints, the neighbor-region edge connectivity and the gradient direction of each edge point, are used to eliminate noncircular edge points. Experimental results show that these two constraints do eliminate noncircular edge points and preserve any circle embedded in edges. The final results show that the proposed method can detect and locate the wheels of a vehicle successfully.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"70 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":"133811883","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
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