Pub Date : 2020-01-01DOI: 10.1007/978-3-030-37548-5
Phoebe Chen, A. Cuzzocrea, Xiaoyong Du, Orhun Kara, Ting Liu, K. Sivalingam, D. Ślęzak, T. Washio, Xiaokang Yang, Junsong Yuan, Simone Diniz Junqueira Barbosa, Chawki Djeddi, Akhtar Jamil, I. Siddiqi, Sabahattin Zaim
{"title":"Pattern Recognition and Artificial Intelligence: Third Mediterranean Conference, MedPRAI 2019, Istanbul, Turkey, December 22–23, 2019, Proceedings","authors":"Phoebe Chen, A. Cuzzocrea, Xiaoyong Du, Orhun Kara, Ting Liu, K. Sivalingam, D. Ślęzak, T. Washio, Xiaokang Yang, Junsong Yuan, Simone Diniz Junqueira Barbosa, Chawki Djeddi, Akhtar Jamil, I. Siddiqi, Sabahattin Zaim","doi":"10.1007/978-3-030-37548-5","DOIUrl":"https://doi.org/10.1007/978-3-030-37548-5","url":null,"abstract":"","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"118 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1007/978-3-030-37548-5","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50962934","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 : 1992-12-01DOI: 10.1109/ICPR.1992.201755
Chung-Lin Huang, Ching-Wen Chen
This paper presents facial features extraction algorithms which can be used for automated visual interpretation and recognition of human faces. It is possible to capture the contours of eye and mouth by deformable template model because of their analytically describable shapes. However, the shapes of eyebrow, nostril and face are difficult to model using a deformable template. They are extracted by using an active contour model, the snake.<>
{"title":"Human facial feature extraction for face interpretation and recognition","authors":"Chung-Lin Huang, Ching-Wen Chen","doi":"10.1109/ICPR.1992.201755","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201755","url":null,"abstract":"This paper presents facial features extraction algorithms which can be used for automated visual interpretation and recognition of human faces. It is possible to capture the contours of eye and mouth by deformable template model because of their analytically describable shapes. However, the shapes of eyebrow, nostril and face are difficult to model using a deformable template. They are extracted by using an active contour model, the snake.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"16 1","pages":"204-207"},"PeriodicalIF":0.0,"publicationDate":"1992-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87763520","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.1992.202140
J. Sanz
Highly parallel systems play a central role in the future of computing. This role is increasing rapidly as the costs involved in improving semiconductor circuit speed and density become higher. The two major hurdles that prevent massive parallelism from becoming mainstream are the relatively slow progress of interconnection networks compared to that of uniprocessor technology and the immature status of parallel software. The paper gives a brief summary of some of the recent advances in the field of highly parallel computing, with an emphasis on message routing architectures.<>
{"title":"Advances in massively parallel computing","authors":"J. Sanz","doi":"10.1109/ICPR.1992.202140","DOIUrl":"https://doi.org/10.1109/ICPR.1992.202140","url":null,"abstract":"Highly parallel systems play a central role in the future of computing. This role is increasing rapidly as the costs involved in improving semiconductor circuit speed and density become higher. The two major hurdles that prevent massive parallelism from becoming mainstream are the relatively slow progress of interconnection networks compared to that of uniprocessor technology and the immature status of parallel software. The paper gives a brief summary of some of the recent advances in the field of highly parallel computing, with an emphasis on message routing architectures.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"32 1","pages":"95-106"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74038464","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.1992.201802
L. Buturovic
Dimension reduction is a process of transforming the multidimensional observations into low-dimensional space. In pattern recognition this process should not cause loss of classification accuracy. This goal is best accomplished using Bayes error as a criterion for dimension reduction. Since the criterion is not usable for practical purposes, the authors suggest the use of the k-nearest neighbor estimate of the Bayes error instead. They experimentally demonstrate the superior performance of the linear dimension reduction algorithm based on this criterion, as compared to the traditional techniques.<>
{"title":"Near-optimal algorithm for dimension reduction","authors":"L. Buturovic","doi":"10.1109/ICPR.1992.201802","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201802","url":null,"abstract":"Dimension reduction is a process of transforming the multidimensional observations into low-dimensional space. In pattern recognition this process should not cause loss of classification accuracy. This goal is best accomplished using Bayes error as a criterion for dimension reduction. Since the criterion is not usable for practical purposes, the authors suggest the use of the k-nearest neighbor estimate of the Bayes error instead. They experimentally demonstrate the superior performance of the linear dimension reduction algorithm based on this criterion, as compared to the traditional techniques.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"8 1","pages":"401-404"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74309469","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.1992.201737
R. B. Huseby, G. Høgåsen, G. Storvik, K. Aas
The paper treats the analysis of an industrial inspection problem, namely the segmentation and discrimination of similar-looking bottles based on a multispectral image consisting of both range and intensity data. A contextual pixel classification is performed using a whole line as neighborhood. The framework of hidden Markov models together with a fast algorithm from control engineering makes this possible. The method is compared to J. Haslett's method (1985) for contextual classification, and performs significantly better.<>
{"title":"Combining range and intensity data with a hidden Markov model","authors":"R. B. Huseby, G. Høgåsen, G. Storvik, K. Aas","doi":"10.1109/ICPR.1992.201737","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201737","url":null,"abstract":"The paper treats the analysis of an industrial inspection problem, namely the segmentation and discrimination of similar-looking bottles based on a multispectral image consisting of both range and intensity data. A contextual pixel classification is performed using a whole line as neighborhood. The framework of hidden Markov models together with a fast algorithm from control engineering makes this possible. The method is compared to J. Haslett's method (1985) for contextual classification, and performs significantly better.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"1 1","pages":"128-131"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73195172","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.1992.201823
J. Tsukumo
Describes a handprinted Kanji character recognition by hierarchical classification based on flexible template matching. In the proposed method, two kinds of flexible template matching are realized by nonlinear shape normalization and by nonlinear pattern matching, based on dynamic programming. The former has the efficiency for local shape restoration and the latter has the efficiency for local shape restoration in handprinted Kanji character variations.<>
{"title":"Handprinted Kanji character recognition based on flexible template matching","authors":"J. Tsukumo","doi":"10.1109/ICPR.1992.201823","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201823","url":null,"abstract":"Describes a handprinted Kanji character recognition by hierarchical classification based on flexible template matching. In the proposed method, two kinds of flexible template matching are realized by nonlinear shape normalization and by nonlinear pattern matching, based on dynamic programming. The former has the efficiency for local shape restoration and the latter has the efficiency for local shape restoration in handprinted Kanji character variations.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"15 1","pages":"483-486"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78373998","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.1992.202121
V. Sundaresan, S. Nichani, N. Ranganathan, R. Sankar
Describes an area and time efficient systolic array architecture for computations in Dynamic Time Warping (DTW). The special purpose architecture is used to perform the band matrix multiplication in order to compute the local distance metric based on Itakura's log likelihood distance. The time complexity of the algorithm is O(nk) where n and k are the number of elements in the row of the first and second input matrices. The number of processors is equal to the bandwidth w of the output band matrix. The speedup of the parallel algorithm compared to the sequential algorithm is wz where z is the multiplier stages within a PE. The parallel algorithm can be implemented as a single VLSI chip.<>
{"title":"A VLSI hardware accelerator for dynamic time warping","authors":"V. Sundaresan, S. Nichani, N. Ranganathan, R. Sankar","doi":"10.1109/ICPR.1992.202121","DOIUrl":"https://doi.org/10.1109/ICPR.1992.202121","url":null,"abstract":"Describes an area and time efficient systolic array architecture for computations in Dynamic Time Warping (DTW). The special purpose architecture is used to perform the band matrix multiplication in order to compute the local distance metric based on Itakura's log likelihood distance. The time complexity of the algorithm is O(nk) where n and k are the number of elements in the row of the first and second input matrices. The number of processors is equal to the bandwidth w of the output band matrix. The speedup of the parallel algorithm compared to the sequential algorithm is wz where z is the multiplier stages within a PE. The parallel algorithm can be implemented as a single VLSI chip.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"23 1","pages":"27-30"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80495956","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.1992.201878
V. Neagoe
Proposes the following cascade for intelligent detection of the presence of binary frequency-shift-keying (FSK) signals corrupted by additive white Gaussian noise: (1) discrete Fourier Transform (DFT) for periodogram estimation, computed at the two modulating frequencies; (2) a specific pattern recognition algorithm in the spectral space IR/sup 2/, consisting of one of the following variants: (a) perceptron; (b) fuzzy perceptron; (c) Bayes. The computer simulation results show the significant improvement of the proposed pattern recognition methods by comparison to the classical technique of detection theory by matched filter. The proposed paper tries to build a bridge between the worlds of communications, signal processing and pattern recognition.<>
{"title":"Seeking pattern recognition principles for intelligent detection of FSK signals","authors":"V. Neagoe","doi":"10.1109/ICPR.1992.201878","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201878","url":null,"abstract":"Proposes the following cascade for intelligent detection of the presence of binary frequency-shift-keying (FSK) signals corrupted by additive white Gaussian noise: (1) discrete Fourier Transform (DFT) for periodogram estimation, computed at the two modulating frequencies; (2) a specific pattern recognition algorithm in the spectral space IR/sup 2/, consisting of one of the following variants: (a) perceptron; (b) fuzzy perceptron; (c) Bayes. The computer simulation results show the significant improvement of the proposed pattern recognition methods by comparison to the classical technique of detection theory by matched filter. The proposed paper tries to build a bridge between the worlds of communications, signal processing and pattern recognition.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"18 1","pages":"721-724"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81849269","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.1992.201848
T. Ojala, M. Pietikäinen, O. Silvén
Pietikainen and Rosenfeld (1982) introduced a class of texture measures based on first-order statistics derived from edges in an image. the objective of this paper is to evaluate the performance of these measures and some new edge-based texture measures using two different types of data sets: images taken from the Brodatz album and images from a practical wood surface inspection problem. The results obtained for edge-based measures are compared to those obtained by popular second-order texture measures and tonal features. The role of the classifier on the performance is also studied by comparing the results obtained for three parametric classifiers and for a nonparametric k-nearest neighbor classifier. The results indicate that edge-based approaches are very promising for surface inspection problems, because they are relatively simple to compute and have performed very well in experiments.<>
{"title":"Edge-based texture measures for surface inspection","authors":"T. Ojala, M. Pietikäinen, O. Silvén","doi":"10.1109/ICPR.1992.201848","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201848","url":null,"abstract":"Pietikainen and Rosenfeld (1982) introduced a class of texture measures based on first-order statistics derived from edges in an image. the objective of this paper is to evaluate the performance of these measures and some new edge-based texture measures using two different types of data sets: images taken from the Brodatz album and images from a practical wood surface inspection problem. The results obtained for edge-based measures are compared to those obtained by popular second-order texture measures and tonal features. The role of the classifier on the performance is also studied by comparing the results obtained for three parametric classifiers and for a nonparametric k-nearest neighbor classifier. The results indicate that edge-based approaches are very promising for surface inspection problems, because they are relatively simple to compute and have performed very well in experiments.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"230 1","pages":"594-598"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73358767","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：