发布求助
文献互助 智能选刊 最新文献

模式识别与人工智能最新文献

筛选
英文 中文
A robust algebraic method for human face recognition 人脸识别的鲁棒代数方法
模式识别与人工智能 Pub Date : 1992-08-30 DOI: 10.1109/ICPR.1992.201759
Yong-Qing Cheng, Ke Liu, Jingyu Yang, Hua-Feng Wang
{"title":"A robust algebraic method for human face recognition","authors":"Yong-Qing Cheng, Ke Liu, Jingyu Yang, Hua-Feng Wang","doi":"10.1109/ICPR.1992.201759","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201759","url":null,"abstract":"The feature image and projective image are first proposed to describe the human face, and a new method for human face recognition in which projective images are used for classification is presented. The projective coordinates of projective image on feature images are used as the feature vectors which represent the inherent attributes of human faces. Finally, the feature extraction method of human face images is derived and a hierarchical distance classifier for human face recognition is constructed. The experiments have shown that the recognition method based on the coordinate feature vector is a powerful method for recognizing human face images, and recognition accuracies of 100 percent are obtained for all 64 facial images in eight classes of human faces.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"33 1","pages":"221-224"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90730511","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: 41
A rotation, scaling and translation invariant pattern classification system 一个旋转、缩放和平移不变模式分类系统
模式识别与人工智能 Pub Date : 1992-08-30 DOI: 10.1109/ICPR.1992.201808
Cem Yüceer, Kemal Oflazer
{"title":"A rotation, scaling and translation invariant pattern classification system","authors":"Cem Yüceer, Kemal Oflazer","doi":"10.1109/ICPR.1992.201808","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201808","url":null,"abstract":"Presents a hybrid pattern classification system which can classify patterns in a rotation, scaling, and translation invariant manner. The system is based on preprocessing the input image to map it into a rotation, scaling, and translation invariant canonical form, which is then classified by a multilayer feedforward neural net. Results from a number of classification problems are also presented in the paper.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"5 1","pages":"422-425"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88831593","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: 66
A probabilistic stroke-based Viterbi algorithm for handwritten Chinese characters recognition 基于概率笔画的Viterbi算法的手写体汉字识别
模式识别与人工智能 Pub Date : 1992-08-30 DOI: 10.1109/ICPR.1992.201752
C. Hsieh, Hsi-Jian Lee
{"title":"A probabilistic stroke-based Viterbi algorithm for handwritten Chinese characters recognition","authors":"C. Hsieh, Hsi-Jian Lee","doi":"10.1109/ICPR.1992.201752","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201752","url":null,"abstract":"This paper presents a probabilistic approach to recognize handwritten Chinese characters. According to the stroke writing sequence, strokes and interleaved stroke relations are built manually as a 1D string, called online models, to describe a Chinese character. The recognition problem is formulated as an optimization process in a multistage directed graph, where the number of stages is the length of the modelled stroke sequence. Nodes in a stage represent extracted strokes. The Viterbi algorithm, which can handle stroke insertion, deletion, splitting, and merging, is applied to compute the similarity between each modelled character and the unknown character. The unknown character is recognized as the one with the highest similarity. Experiments with 500 characters uniformly selected from the database CCL/HCCR1 are conducted, and the recognition rate is about 94.3%.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"5 1","pages":"191-194"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76641575","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: 15
An optimization algorithm for determining the compatibility coefficients of relaxation labeling processes 一种确定松弛标记过程相容系数的优化算法
模式识别与人工智能 Pub Date : 1992-08-30 DOI: 10.1109/ICPR.1992.201741
M. Pelillo, M. Refice
{"title":"An optimization algorithm for determining the compatibility coefficients of relaxation labeling processes","authors":"M. Pelillo, M. Refice","doi":"10.1109/ICPR.1992.201741","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201741","url":null,"abstract":"The problem of determining compatibility coefficients for relaxation labeling processes has received considerable attention and a number of different methods have been suggested. The authors propose a method developed within an optimization framework. After formulating the problem of determining the coefficients as a nonlinear programming problem, they develop a gradient-descent algorithm for solving it. Results on an application of relaxation processes are given.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"79 1","pages":"145-148"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76651307","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
Flexible real-time programming of a distributed transputer-based vision system 基于分布式传输器的视觉系统的灵活实时编程
模式识别与人工智能 Pub Date : 1992-08-30 DOI: 10.1109/ICPR.1992.202148
G. Schwingshakl, W. Pölzleitner
{"title":"Flexible real-time programming of a distributed transputer-based vision system","authors":"G. Schwingshakl, W. Pölzleitner","doi":"10.1109/ICPR.1992.202148","DOIUrl":"https://doi.org/10.1109/ICPR.1992.202148","url":null,"abstract":"The authors describe the major aspects in their transputer-based automatic vision system (TAVS) aiming to implement a scaleable and easily reconfigurable system, in which the mapping of image processing and recognition algorithms to the hardware is facilitated by automatic code generation schemes, separating methodic design and implementation details. The paper presents the system design and underlying hardware architecture first. The authors describe the modules available for iconic image processing and feature extraction and selection. The code generation for the hierarchical statistical decision network is then described, followed by the implementation of the language pi for process allocation. The various system parts were tested in an implementation of real-time wooden board inspection. For this example the authors present details on typical algorithms and how they were implemented on a maintainable and scaleable industrial system.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"68 1","pages":"133-135"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84061376","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: 0
Transducer learning in pattern recognition 模式识别中的传感器学习
模式识别与人工智能 Pub Date : 1992-08-30 DOI: 10.1109/ICPR.1992.201777
J. Oncina, P. García, E. Vidal
{"title":"Transducer learning in pattern recognition","authors":"J. Oncina, P. García, E. Vidal","doi":"10.1109/ICPR.1992.201777","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201777","url":null,"abstract":"'Interpretation' is a general and interesting pattern recognition framework in which a system is considered to input object representations, and output the corresponding interpretations in terms of 'semantic messages' specifying the actions to be carried out as system's responses. From the syntactic pattern recognition viewpoint, interpretation reduces to formal transduction. The authors propose an efficient and effective algorithm to automatically infer a finite state transducer from a training set of input-output examples of the interpretation problem considered. The proposed algorithm has been shown to identify an important class of transductions known as 'subsequential transductions.' Experimental results are presented showing the performance and capabilities of the proposed method.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"30 1","pages":"299-302"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88029828","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
A hidden Markov model for language syntax in text recognition 文本识别中语言语法的隐马尔可夫模型
模式识别与人工智能 Pub Date : 1992-08-30 DOI: 10.1109/ICPR.1992.201736
J. Hull
{"title":"A hidden Markov model for language syntax in text recognition","authors":"J. Hull","doi":"10.1109/ICPR.1992.201736","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201736","url":null,"abstract":"The use of a hidden Markov model (HMM) for language syntax to improve the performance of a text recognition algorithm is proposed. Syntactic constraints are described by the transition probabilities between word classes. The confusion between the feature string for a word and the various syntactic classes is also described probabilistically. A modification of the Viterbi algorithm is also proposed that finds a fixed number of sequences of syntactic classes for a given sentence that have the highest probabilities of occurrence, given the feature strings for the words. An experimental application of this approach is demonstrated with a word hypothesization algorithm that produces a number of guesses about the identity of each word in a running text. The use of first and second order transition probabilities is explored. Overall performance of between 65 and 80 percent reduction in the average number of words that can match a given image is achieved.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"11 1","pages":"124-127"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83113265","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: 24
Text data extraction from microfilm images of punched cards 从穿孔卡片的缩微胶片图像中提取文本数据
模式识别与人工智能 Pub Date : 1992-08-30 DOI: 10.1109/ICPR.1992.201761
Sudha U. Kumar, R. Kasturi
{"title":"Text data extraction from microfilm images of punched cards","authors":"Sudha U. Kumar, R. Kasturi","doi":"10.1109/ICPR.1992.201761","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201761","url":null,"abstract":"A system for reading text data from microfilm images of punched cards is described. The input is a high resolution gray level image obtained by scanning the card image from the microfilm. Noise due to the poor quality of microfilm data and similarity in gray levels of noise patches and punches are the major problems for text extraction. Thresholding, skew correction and morphological operations are performed on the input gray level image. Card parameters such as positions of punches, etc., are calculated and used along with the knowledge about the contents of the card to separate punched holes from other artifacts. Text data are recognized by locating the punched holes and errors are corrected by a context-based approach. The algorithm has been implemented in software and tested on several images.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"6 1","pages":"230-233"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84323667","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
A real-time VLSI-based architecture for multi-motion estimation 基于vlsi的实时多运动估计体系结构
模式识别与人工智能 Pub Date : 1992-08-30 DOI: 10.1109/ICPR.1992.202152
J. Legat, J. Cornil, D. Macq, M. Verleysen
{"title":"A real-time VLSI-based architecture for multi-motion estimation","authors":"J. Legat, J. Cornil, D. Macq, M. Verleysen","doi":"10.1109/ICPR.1992.202152","DOIUrl":"https://doi.org/10.1109/ICPR.1992.202152","url":null,"abstract":"This paper describes a new parallel architecture dedicated to multi-motion estimation. The input image is scanned by a standard video camera with 256 grey levels. Motion computing is based on the optical flow determination. Some constraints are proposed to allow multi-motion evaluation. The algorithm is presented and the main features of a 1-D systolic architecture which is based on a custom VLSI chip is given. This architecture allows a real-time implementation of the multi-motion estimation algorithm.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"67 1","pages":"147-150"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82343909","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: 0
Feedforward neural networks with random weights 具有随机权重的前馈神经网络
模式识别与人工智能 Pub Date : 1992-08-30 DOI: 10.1109/ICPR.1992.201708
W. F. Schmidt, M. Kraaijveld, R. Duin
{"title":"Feedforward neural networks with random weights","authors":"W. F. Schmidt, M. Kraaijveld, R. Duin","doi":"10.1109/ICPR.1992.201708","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201708","url":null,"abstract":"In the field of neural network research a number of experiments described seem to be in contradiction with the classical pattern recognition or statistical estimation theory. The authors attempt to give some experimental understanding why this could be possible by showing that a large fraction of the parameters (the weights of neural networks) are of less importance and do not need to be measured with high accuracy. The remaining part is capable to implement the desired classifier and because this is only a small fraction of the total number of weights, the reported experiments seem to be more realistic from a classical point of view.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"20 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81551606","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: 548
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