Pub Date : 1992-08-30DOI: 10.1109/ICPR.1992.201840
L. Micó, J. Oncina, E. Vidal
Given a set of n points or 'prototypes' and another point or 'test sample'. The authors present an algorithm that finds a prototype that is a nearest neighbour of the test sample, by computing only a constant number of distances on the average. This is achieved through a preprocessing procedure that computes only a number of distances and uses an amount of memory that grows lineally with n. The algorithm is an improvement of the previously introduced AESA algorithm and, as such, does not assume the data to be structured into a vector space, making only use of the metric properties of the given distance.<>
{"title":"An algorithm for finding nearest neighbours in constant average time with a linear space complexity","authors":"L. Micó, J. Oncina, E. Vidal","doi":"10.1109/ICPR.1992.201840","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201840","url":null,"abstract":"Given a set of n points or 'prototypes' and another point or 'test sample'. The authors present an algorithm that finds a prototype that is a nearest neighbour of the test sample, by computing only a constant number of distances on the average. This is achieved through a preprocessing procedure that computes only a number of distances and uses an amount of memory that grows lineally with n. The algorithm is an improvement of the previously introduced AESA algorithm and, as such, does not assume the data to be structured into a vector space, making only use of the metric properties of the given distance.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"4 1","pages":"557-560"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82108236","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}
Pub Date : 1992-08-30DOI: 10.1109/ICPR.1992.201801
X. Zhuang, Y. Huang
Designs the optimal learning rule for the Hopfield associative memories (HAM) based on three well recognized criteria, that is, all desired attractors must be made not only isolately stable but also asymptotically stable, and the spurious stable states should be the fewest possible. To construct a satisfactory HAM, those criteria are crucial. The paper first analyzes the real cause of the unsatisfactory performance of the Hebb rule and many other existing learning rules designed for HAMs and then show that three criteria actually amount to widely expanding the basin of attraction around each desired attractor. One effective way to widely expand basins of attraction of all desired attractors is to appropriately dig their respective steep kernal basin of attraction. For this, the authors introduce a concept called the Hamming-stability. The Hamming-stability for all desired attractors can be reduced to a moderately expansive linear separability condition at each neuron and thus the well known Rosenblatt's perceptron learning rule is the right one for learning the Hamming-stability. Extensive and systematic experiments were conducted, convincingly showing that the proposed perceptron. Hamming-stability learning rule did take a good care of three optimal criteria.<>
{"title":"Optimal learning for Hopfield associative memory","authors":"X. Zhuang, Y. Huang","doi":"10.1109/ICPR.1992.201801","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201801","url":null,"abstract":"Designs the optimal learning rule for the Hopfield associative memories (HAM) based on three well recognized criteria, that is, all desired attractors must be made not only isolately stable but also asymptotically stable, and the spurious stable states should be the fewest possible. To construct a satisfactory HAM, those criteria are crucial. The paper first analyzes the real cause of the unsatisfactory performance of the Hebb rule and many other existing learning rules designed for HAMs and then show that three criteria actually amount to widely expanding the basin of attraction around each desired attractor. One effective way to widely expand basins of attraction of all desired attractors is to appropriately dig their respective steep kernal basin of attraction. For this, the authors introduce a concept called the Hamming-stability. The Hamming-stability for all desired attractors can be reduced to a moderately expansive linear separability condition at each neuron and thus the well known Rosenblatt's perceptron learning rule is the right one for learning the Hamming-stability. Extensive and systematic experiments were conducted, convincingly showing that the proposed perceptron. Hamming-stability learning rule did take a good care of three optimal criteria.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"37 1","pages":"397-400"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87088814","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}
Pub Date : 1992-08-30DOI: 10.1109/ICPR.1992.201696
M. Berthod, Shan Yu, J. Stromboni
Proposes deterministic psuedo annealing (DPA), a variation of simulated annealing. The method is an extension of relaxation labeling, a once popular framework for a variety of computer vision problems. The authors present its application to textured image segmentation. The basic idea is to introduce weighted labelings, which assign a weighted combination of labels to any site, and then to build a merit function of all the weighted labels. This function, a polynomial with non-negative coefficients, is an extension to a compact domain of R/sup N/ of an application defined on the finite (but very large) set of labelings; its only extrema under suitable constraints correspond to discrete labelings. DPA consists of changing the constraints, and thus the domain, so as to convexify this function, find its unique global maximum, and then track down the solution until the original constraints are restored, thus obtaining usually good discrete labeling.<>
{"title":"Deterministic pseudo-annealing: a new optimization scheme applied to texture segmentation","authors":"M. Berthod, Shan Yu, J. Stromboni","doi":"10.1109/ICPR.1992.201696","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201696","url":null,"abstract":"Proposes deterministic psuedo annealing (DPA), a variation of simulated annealing. The method is an extension of relaxation labeling, a once popular framework for a variety of computer vision problems. The authors present its application to textured image segmentation. The basic idea is to introduce weighted labelings, which assign a weighted combination of labels to any site, and then to build a merit function of all the weighted labels. This function, a polynomial with non-negative coefficients, is an extension to a compact domain of R/sup N/ of an application defined on the finite (but very large) set of labelings; its only extrema under suitable constraints correspond to discrete labelings. DPA consists of changing the constraints, and thus the domain, so as to convexify this function, find its unique global maximum, and then track down the solution until the original constraints are restored, thus obtaining usually good discrete labeling.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"22 1","pages":"533-536"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82745715","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}
Pub Date : 1992-08-30DOI: 10.1109/ICPR.1992.202118
M. Patel, P. McCabe, N. Ranganathan
Describes the design and implementation of a two-dimensional systolic array processor for applications in image processing and computer vision. The processor architecture is based on a SIMD array of 4-bit processing elements, interconnected by a mesh network with four nearest neighbors. The PE array is programmable allowing the user to develop application-specific algorithms for performing analysis on image data. A prototype VLSI chip has been designed implementing a single PE and has been submitted for fabrication. The chip is expected to operate at 25 MHz.<>
{"title":"SIBA: a VLSI systolic array chip for image processing","authors":"M. Patel, P. McCabe, N. Ranganathan","doi":"10.1109/ICPR.1992.202118","DOIUrl":"https://doi.org/10.1109/ICPR.1992.202118","url":null,"abstract":"Describes the design and implementation of a two-dimensional systolic array processor for applications in image processing and computer vision. The processor architecture is based on a SIMD array of 4-bit processing elements, interconnected by a mesh network with four nearest neighbors. The PE array is programmable allowing the user to develop application-specific algorithms for performing analysis on image data. A prototype VLSI chip has been designed implementing a single PE and has been submitted for fabrication. The chip is expected to operate at 25 MHz.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"5 1","pages":"15-18"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88881135","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}
Pub Date : 1992-08-30DOI: 10.1109/ICPR.1992.201771
Franck Lebourgeois, Z. Bublinski, H. Emptoz
Outlines a fast and efficient method for extracting graphics and text paragraphs from printed documents. The method presented is based on bottom-up approach to document analysis and it achieves very good performance in most cases. During the preprocessing characters are linked together to form blocks. Created blocks are segmented, labelled and merged into paragraphs. Simultaneously, graphics are extracted from the image. Algorithms for each step of processing are presented. Also, the obtained experimental results are included.<>
{"title":"A fast and efficient method for extracting text paragraphs and graphics from unconstrained documents","authors":"Franck Lebourgeois, Z. Bublinski, H. Emptoz","doi":"10.1109/ICPR.1992.201771","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201771","url":null,"abstract":"Outlines a fast and efficient method for extracting graphics and text paragraphs from printed documents. The method presented is based on bottom-up approach to document analysis and it achieves very good performance in most cases. During the preprocessing characters are linked together to form blocks. Created blocks are segmented, labelled and merged into paragraphs. Simultaneously, graphics are extracted from the image. Algorithms for each step of processing are presented. Also, the obtained experimental results are included.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"99 1","pages":"272-276"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88535355","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}
Pub Date : 1992-08-30DOI: 10.1109/ICPR.1992.201776
Hoda Fahmy, D. Blostein
Graph grammars provide a useful formalism for describing structural manipulations of multidimensional data. The authors review briefly theoretical aspects of graph grammars, particularly of the embedding problem, and then summarize graph-grammar applications. Currently graph grammars are used most successfully in application areas other than pattern recognition. Widespread application of graph grammars to picture processing tasks will require research into problems of large-scale grammars, readability of grammars, and grammatical processing of uncertain data.<>
{"title":"A survey of graph grammars: theory and applications","authors":"Hoda Fahmy, D. Blostein","doi":"10.1109/ICPR.1992.201776","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201776","url":null,"abstract":"Graph grammars provide a useful formalism for describing structural manipulations of multidimensional data. The authors review briefly theoretical aspects of graph grammars, particularly of the embedding problem, and then summarize graph-grammar applications. Currently graph grammars are used most successfully in application areas other than pattern recognition. Widespread application of graph grammars to picture processing tasks will require research into problems of large-scale grammars, readability of grammars, and grammatical processing of uncertain data.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"111 1","pages":"294-298"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90911369","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}
Pub Date : 1992-08-30DOI: 10.1109/ICPR.1992.201732
R. Haralick
This paper gives a brief overview of the classical contextual pattern recognition problem. It is shown that the difficulty of this problem is really associated with the determination and use of the support of the joint prior distribution of the category labels. It is indicated how the consistent labeling framework can be used to define the support of the joint prior. It is then shown that this formulation of the problem can be generalized, and a general propositional logic framework which not only defines the support of the joint prior but also permits a calculation to be made evaluating the joint prior for any given set of joint labelings is introduced. It is shown that this formulation is indeed a formulation relating to the degree of belief. A formal system for the degree of belief in terms of an operational probability meaning is developed. The degree of belief in a proposition is exactly the probability with which the proposition can be asserted. It is then shown how the classical contextual problem can be generalized in the belief framework.<>
{"title":"Contextual decision making with degrees of belief","authors":"R. Haralick","doi":"10.1109/ICPR.1992.201732","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201732","url":null,"abstract":"This paper gives a brief overview of the classical contextual pattern recognition problem. It is shown that the difficulty of this problem is really associated with the determination and use of the support of the joint prior distribution of the category labels. It is indicated how the consistent labeling framework can be used to define the support of the joint prior. It is then shown that this formulation of the problem can be generalized, and a general propositional logic framework which not only defines the support of the joint prior but also permits a calculation to be made evaluating the joint prior for any given set of joint labelings is introduced. It is shown that this formulation is indeed a formulation relating to the degree of belief. A formal system for the degree of belief in terms of an operational probability meaning is developed. The degree of belief in a proposition is exactly the probability with which the proposition can be asserted. It is then shown how the classical contextual problem can be generalized in the belief framework.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"73 1","pages":"105-111"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76598660","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}
Pub Date : 1992-08-30DOI: 10.1109/ICPR.1992.202159
M. Cavaiuolo, A. Yakovleff, J. Kershaw, C. R. Watson, D. A. Krnak
For the analysis of motion in near real-time there are very high computational requirements. This is a limiting factor in the hardware implementation of such real-time systems. This application, however, is possible if implemented in the form of some parallel architecture. Neural network structures comprising a large number of simple processing elements can offer a solution to achieving the performance requirements of real-time motion analysis. This paper describes the Neural Accelerator, which is based on a systolic array architecture, and how it can be set up to sense the position and range of an object relative to the observer who is travelling towards it.<>
{"title":"Motion analysis using the neural accelerator board","authors":"M. Cavaiuolo, A. Yakovleff, J. Kershaw, C. R. Watson, D. A. Krnak","doi":"10.1109/ICPR.1992.202159","DOIUrl":"https://doi.org/10.1109/ICPR.1992.202159","url":null,"abstract":"For the analysis of motion in near real-time there are very high computational requirements. This is a limiting factor in the hardware implementation of such real-time systems. This application, however, is possible if implemented in the form of some parallel architecture. Neural network structures comprising a large number of simple processing elements can offer a solution to achieving the performance requirements of real-time motion analysis. This paper describes the Neural Accelerator, which is based on a systolic array architecture, and how it can be set up to sense the position and range of an object relative to the observer who is travelling towards it.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"16 1","pages":"173-176"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75194305","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}
Pub Date : 1992-08-30DOI: 10.1109/ICPR.1992.202151
P. Jonker, E. Komen
To speed up image processing in the field of robot vision and industrial inspection, a pipeline element was made which is able to perform fast cellular logic operations. This Cellular Logic Processing Element (CLPE) is able to process binary images with a speed of 100 ns per pixel. The processing element is a CMOS VLSI-device which includes a Writable Logic Array for the storage of sets of 3*3 structuring elements which define the cellular logic operations. This paper describes how such CLPEs can be used for building a pipeline for mixed grey value processing and cellular logic processing.<>
{"title":"A scalable real-time image processing pipeline","authors":"P. Jonker, E. Komen","doi":"10.1109/ICPR.1992.202151","DOIUrl":"https://doi.org/10.1109/ICPR.1992.202151","url":null,"abstract":"To speed up image processing in the field of robot vision and industrial inspection, a pipeline element was made which is able to perform fast cellular logic operations. This Cellular Logic Processing Element (CLPE) is able to process binary images with a speed of 100 ns per pixel. The processing element is a CMOS VLSI-device which includes a Writable Logic Array for the storage of sets of 3*3 structuring elements which define the cellular logic operations. This paper describes how such CLPEs can be used for building a pipeline for mixed grey value processing and cellular logic processing.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"115 1","pages":"142-146"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75335237","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}
Pub Date : 1992-08-30DOI: 10.1109/ICPR.1992.201697
J. C. Anigbogu, A. Belaïd
Presents a performance analysis of a first order hidden Markov model based OCR system. Trade-offs between accuracy in terms of recognition rates and complexity in terms of the number of states in the model are discussed. For most fonts, optimal performance is achieved with 6-state models. With adequate heuristics and reliable post-processors, 5-state and even 4-state models give reasonable performances (up to 99.60% at 4-states).<>
{"title":"Performance evaluation of an HMM based OCR system","authors":"J. C. Anigbogu, A. Belaïd","doi":"10.1109/ICPR.1992.201697","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201697","url":null,"abstract":"Presents a performance analysis of a first order hidden Markov model based OCR system. Trade-offs between accuracy in terms of recognition rates and complexity in terms of the number of states in the model are discussed. For most fonts, optimal performance is achieved with 6-state models. With adequate heuristics and reliable post-processors, 5-state and even 4-state models give reasonable performances (up to 99.60% at 4-states).<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"34 1","pages":"565-568"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73405401","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：