Pub Date : 1995-08-14DOI: 10.1109/ICDAR.1995.599033
Hsi-Jian Lee, Cheng-Huang Tung
This paper presents a new method for clustering the words in a dictionary into word groups, which are applied in a Chinese character recognition system with a language model to describe the contextual information. The Chinese synonym dictionary Tong2yi4ci2 ci2lin2 providing the semantic features is used to train the weights of the semantic attributes of the character-based word classes. The weights of the semantic attributes are next updated according to the words of the behavior dictionary, which has a rather complete word set. Then, the updated word classes are clustered into m groups according to the semantic measurement by a greedy method. The words in the behavior dictionary can finally be assigned into the m groups. The parameter space for bigram contextual information of the character recognition system is m/sup 2/. From the experimental results, the recognition system with the proposed model has shown better performance than that of a character-based bigram language model.
{"title":"A language model based on semantically clustered words in a Chinese character recognition system","authors":"Hsi-Jian Lee, Cheng-Huang Tung","doi":"10.1109/ICDAR.1995.599033","DOIUrl":"https://doi.org/10.1109/ICDAR.1995.599033","url":null,"abstract":"This paper presents a new method for clustering the words in a dictionary into word groups, which are applied in a Chinese character recognition system with a language model to describe the contextual information. The Chinese synonym dictionary Tong2yi4ci2 ci2lin2 providing the semantic features is used to train the weights of the semantic attributes of the character-based word classes. The weights of the semantic attributes are next updated according to the words of the behavior dictionary, which has a rather complete word set. Then, the updated word classes are clustered into m groups according to the semantic measurement by a greedy method. The words in the behavior dictionary can finally be assigned into the m groups. The parameter space for bigram contextual information of the character recognition system is m/sup 2/. From the experimental results, the recognition system with the proposed model has shown better performance than that of a character-based bigram language model.","PeriodicalId":273519,"journal":{"name":"Proceedings of 3rd International Conference on Document Analysis and Recognition","volume":"172 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132794036","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 : 1995-08-14DOI: 10.1109/ICDAR.1995.601979
Yi Lu, A. Tisler
The extraction of lines, words and characters from a digital document image are necessary computational steps preceding character recognition. Much has been discussed in character segmentation and recognition but little has been done in the area of line and word segmentation. The authors present two special filters, minimum difference filters (MDF) and average difference filters (ADF) to facilitate line and word segmentation. They discuss how to select the scales of these filters dynamically and how to use the filters to eliminate crossing lines from a text image.
{"title":"Gray scale filtering for line and word segmentation","authors":"Yi Lu, A. Tisler","doi":"10.1109/ICDAR.1995.601979","DOIUrl":"https://doi.org/10.1109/ICDAR.1995.601979","url":null,"abstract":"The extraction of lines, words and characters from a digital document image are necessary computational steps preceding character recognition. Much has been discussed in character segmentation and recognition but little has been done in the area of line and word segmentation. The authors present two special filters, minimum difference filters (MDF) and average difference filters (ADF) to facilitate line and word segmentation. They discuss how to select the scales of these filters dynamically and how to use the filters to eliminate crossing lines from a text image.","PeriodicalId":273519,"journal":{"name":"Proceedings of 3rd International Conference on Document Analysis and Recognition","volume":"159 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133641941","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 : 1995-08-14DOI: 10.1109/ICDAR.1995.602080
G. Congedo, G. Dimauro, S. Impedovo, G. Pirlo
This paper presents a complete procedure for the segmentation of handwritten numeric strings. The procedure uses an hypothesis-then-verification strategy in which multiple segmentation algorithms based on contiguous row partition work sequentially on the binary image until an acceptable segmentation is obtained. At this purpose a new set of algorithms simulating a "drop falling" process is introduced. The experimental tests demonstrate the effectiveness of the new algorithms in obtaining high-confidence segmentation hypotheses.
{"title":"Segmentation of numeric strings","authors":"G. Congedo, G. Dimauro, S. Impedovo, G. Pirlo","doi":"10.1109/ICDAR.1995.602080","DOIUrl":"https://doi.org/10.1109/ICDAR.1995.602080","url":null,"abstract":"This paper presents a complete procedure for the segmentation of handwritten numeric strings. The procedure uses an hypothesis-then-verification strategy in which multiple segmentation algorithms based on contiguous row partition work sequentially on the binary image until an acceptable segmentation is obtained. At this purpose a new set of algorithms simulating a \"drop falling\" process is introduced. The experimental tests demonstrate the effectiveness of the new algorithms in obtaining high-confidence segmentation hypotheses.","PeriodicalId":273519,"journal":{"name":"Proceedings of 3rd International Conference on Document Analysis and Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117101132","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 : 1995-08-14DOI: 10.1109/ICDAR.1995.599026
Ann Grbavec, D. Blostein
This paper investigates graph rewriting as a tool for high-level recognition of two-dimensional mathematical notation. "High-level recognition" is the process of determining the meaning of a diagram from the output of a symbol recognizer. Characteristic problems of high-level mathematics recognition include: determining the groupings of symbols into recursive subexpressions and resolving ambiguities that depend upon global context. Our graph-rewriting approach uses knowledge of the notational conventions of mathematics, such as operator precedence and operator range, more effectively than syntactic or previous structural methods. Graph rewriting offers a flexible formalism with a strong theoretical foundation for manipulating two-dimensional patterns. It has been shown to be a useful technique for high-level recognition of circuit diagrams and musical scores. By demonstrating a graph-rewriting strategy for mathematics recognition, this paper provides further evidence for graph rewriting as a general tool for diagram recognition, and identifies some of the issues that must be considered as this potential is explored.
{"title":"Mathematics recognition using graph rewriting","authors":"Ann Grbavec, D. Blostein","doi":"10.1109/ICDAR.1995.599026","DOIUrl":"https://doi.org/10.1109/ICDAR.1995.599026","url":null,"abstract":"This paper investigates graph rewriting as a tool for high-level recognition of two-dimensional mathematical notation. \"High-level recognition\" is the process of determining the meaning of a diagram from the output of a symbol recognizer. Characteristic problems of high-level mathematics recognition include: determining the groupings of symbols into recursive subexpressions and resolving ambiguities that depend upon global context. Our graph-rewriting approach uses knowledge of the notational conventions of mathematics, such as operator precedence and operator range, more effectively than syntactic or previous structural methods. Graph rewriting offers a flexible formalism with a strong theoretical foundation for manipulating two-dimensional patterns. It has been shown to be a useful technique for high-level recognition of circuit diagrams and musical scores. By demonstrating a graph-rewriting strategy for mathematics recognition, this paper provides further evidence for graph rewriting as a general tool for diagram recognition, and identifies some of the issues that must be considered as this potential is explored.","PeriodicalId":273519,"journal":{"name":"Proceedings of 3rd International Conference on Document Analysis and Recognition","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116510208","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 : 1995-08-14DOI: 10.1109/ICDAR.1995.601987
Myoung-Young Yoon, Seong-Whan Lee, Ju-Sung Kim
We present a new scheme for the restoration of faxed images degraded by both salient noise and additive white noise. We consider two fundamental aspects of faxed image restoration: modeling and the restoration algorithm. First, a model of a faxed image is presented. The model is based on an autoregressive Gauss-Markov random field and includes vertical and horizontal overlap effects. In particular, we concentrate on the nonsymmetric half plane causality. Second, the restoration of faxed images degraded by salient noise and additive white noise is considered by 2D Kalman filtering which provides an efficient recursive procedure. In order to illustrate the effectiveness of the proposed scheme, we present experimental results on the restoration of a faxed image.
{"title":"Faxed image restoration using Kalman filtering","authors":"Myoung-Young Yoon, Seong-Whan Lee, Ju-Sung Kim","doi":"10.1109/ICDAR.1995.601987","DOIUrl":"https://doi.org/10.1109/ICDAR.1995.601987","url":null,"abstract":"We present a new scheme for the restoration of faxed images degraded by both salient noise and additive white noise. We consider two fundamental aspects of faxed image restoration: modeling and the restoration algorithm. First, a model of a faxed image is presented. The model is based on an autoregressive Gauss-Markov random field and includes vertical and horizontal overlap effects. In particular, we concentrate on the nonsymmetric half plane causality. Second, the restoration of faxed images degraded by salient noise and additive white noise is considered by 2D Kalman filtering which provides an efficient recursive procedure. In order to illustrate the effectiveness of the proposed scheme, we present experimental results on the restoration of a faxed image.","PeriodicalId":273519,"journal":{"name":"Proceedings of 3rd International Conference on Document Analysis and Recognition","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115675755","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 : 1995-08-14DOI: 10.1109/ICDAR.1995.602066
Francis Y. L. Chin, Francis Wu
Magnetic Ink Character Recognition (MICR) technology has widely been used for processing bank checks. Since the MICR character set is a special type font, and the ink is also readable by human being, optical approach can also be used. This report will describe the design of a low-cost, but highly accurate, microprocessor-based optical character recognition (OCR) check reader. The performance of our OCR reader is affected by a number of factors, mainly the noise generated by the lens system and the colour image at the check background. In this paper we describe how our software solution can alleviate these problems. As speed is another concern, special attention is paid to the design of recognition algorithm, such as the avoidance of floating point arithmetics, hardware limitations, etc.
{"title":"A microprocessor-based optical character recognition check reader","authors":"Francis Y. L. Chin, Francis Wu","doi":"10.1109/ICDAR.1995.602066","DOIUrl":"https://doi.org/10.1109/ICDAR.1995.602066","url":null,"abstract":"Magnetic Ink Character Recognition (MICR) technology has widely been used for processing bank checks. Since the MICR character set is a special type font, and the ink is also readable by human being, optical approach can also be used. This report will describe the design of a low-cost, but highly accurate, microprocessor-based optical character recognition (OCR) check reader. The performance of our OCR reader is affected by a number of factors, mainly the noise generated by the lens system and the colour image at the check background. In this paper we describe how our software solution can alleviate these problems. As speed is another concern, special attention is paid to the design of recognition algorithm, such as the avoidance of floating point arithmetics, hardware limitations, etc.","PeriodicalId":273519,"journal":{"name":"Proceedings of 3rd International Conference on Document Analysis and Recognition","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121754232","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 : 1995-08-14DOI: 10.1109/ICDAR.1995.599000
K. Gyohten, Tomoko Sumiya, N. Babaguchi, K. Kakusho, T. Kitahashi
In this paper, we present COCE (COordinative Character Extractor), a new method for extracting printed Japanese characters from an unformatted document image. This research aims to exploit knowledge independent of the layouts. COCE is based on a multiagent scheme where each agent is assigned to a single character line and tries to extract characters by making use of the knowledge about features of a character line as well as shapes and arrangement of characters. Moreover, the agents communicate with each other to keep consistency between their tasks. We have favourable results for the effectiveness of this method.
本文提出了一种从未格式化文档图像中提取打印日文字符的新方法COCE (coordinated Character Extractor)。本研究旨在开发与布局无关的知识。COCE基于多智能体方案，每个智能体被分配到单个字符线，并试图利用有关字符线的特征以及字符的形状和排列的知识来提取字符。此外，代理之间相互通信以保持其任务之间的一致性。我们对这种方法的有效性有良好的结果。
{"title":"Extracting characters and character lines in multi-agent scheme","authors":"K. Gyohten, Tomoko Sumiya, N. Babaguchi, K. Kakusho, T. Kitahashi","doi":"10.1109/ICDAR.1995.599000","DOIUrl":"https://doi.org/10.1109/ICDAR.1995.599000","url":null,"abstract":"In this paper, we present COCE (COordinative Character Extractor), a new method for extracting printed Japanese characters from an unformatted document image. This research aims to exploit knowledge independent of the layouts. COCE is based on a multiagent scheme where each agent is assigned to a single character line and tries to extract characters by making use of the knowledge about features of a character line as well as shapes and arrangement of characters. Moreover, the agents communicate with each other to keep consistency between their tasks. We have favourable results for the effectiveness of this method.","PeriodicalId":273519,"journal":{"name":"Proceedings of 3rd International Conference on Document Analysis and Recognition","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123198255","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 : 1995-08-14DOI: 10.1109/ICDAR.1995.602043
Seung-Ho Lee, Hyunkyu Lee, J. H. Kim
A new approach for on-line cursive script recognition that combines a letter spotting technique with an island-driven lattice search algorithm is presented. Initially, all plausible letter components within an input pattern are detected, using a letter spotting technique based on hidden Markov models. A word hypothesis lattice is generated as a result of the letter spotting. Then an island-driven search algorithm is performed to find the optimal path on the word hypothesis lattice, which corresponds to the most probable word among the dictionary words. The results of this experiment suggest that the proposed method works effectively in recognizing English cursive words. In a word recognition test, the average 85.4% word accuracy was obtained.
{"title":"On-line cursive script recognition using an island-driven search technique","authors":"Seung-Ho Lee, Hyunkyu Lee, J. H. Kim","doi":"10.1109/ICDAR.1995.602043","DOIUrl":"https://doi.org/10.1109/ICDAR.1995.602043","url":null,"abstract":"A new approach for on-line cursive script recognition that combines a letter spotting technique with an island-driven lattice search algorithm is presented. Initially, all plausible letter components within an input pattern are detected, using a letter spotting technique based on hidden Markov models. A word hypothesis lattice is generated as a result of the letter spotting. Then an island-driven search algorithm is performed to find the optimal path on the word hypothesis lattice, which corresponds to the most probable word among the dictionary words. The results of this experiment suggest that the proposed method works effectively in recognizing English cursive words. In a word recognition test, the average 85.4% word accuracy was obtained.","PeriodicalId":273519,"journal":{"name":"Proceedings of 3rd International Conference on Document Analysis and Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124377857","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 : 1995-08-14DOI: 10.1109/ICDAR.1995.601976
Moon-Soo Chang, S. Kang, Woo-Sik Rho, Heok-Gu Kim, Duck-Jin Kim
A binarization method is presented to counter the stroke connectivity problems of characters arising from mid-level-quality binary image scanning systems. In the output of a binary image scanning system, separate strokes may look connected if the point size is small and the character strokes are complex while strokes may lose connectivity if they are generated at low intensity. Also, erroneous recognition may result if a blemished document surface distorts the image. To counter these problems and to further enhance the quality of character recognition, the authors have developed an integrated binarization scheme, exploiting synergistic use of an adaptive thresholding technique and variable histogram equalization. This algorithm is composed of two components. The first removes background noise via gray level histogram equalization while the second enhances the gray level of characters over and above the surrounding background via an edge image composition technique.
{"title":"Improved binarization algorithm for document image by histogram and edge detection","authors":"Moon-Soo Chang, S. Kang, Woo-Sik Rho, Heok-Gu Kim, Duck-Jin Kim","doi":"10.1109/ICDAR.1995.601976","DOIUrl":"https://doi.org/10.1109/ICDAR.1995.601976","url":null,"abstract":"A binarization method is presented to counter the stroke connectivity problems of characters arising from mid-level-quality binary image scanning systems. In the output of a binary image scanning system, separate strokes may look connected if the point size is small and the character strokes are complex while strokes may lose connectivity if they are generated at low intensity. Also, erroneous recognition may result if a blemished document surface distorts the image. To counter these problems and to further enhance the quality of character recognition, the authors have developed an integrated binarization scheme, exploiting synergistic use of an adaptive thresholding technique and variable histogram equalization. This algorithm is composed of two components. The first removes background noise via gray level histogram equalization while the second enhances the gray level of characters over and above the surrounding background via an edge image composition technique.","PeriodicalId":273519,"journal":{"name":"Proceedings of 3rd International Conference on Document Analysis and Recognition","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128540205","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 : 1995-08-14DOI: 10.1109/ICDAR.1995.602126
Su S. Chen, R. Haralick, I. T. Phillips
This paper describes an algorithm to estimate the text skew angle in a document image. The algorithm utilizes the recursive morphological transforms and yields accurate estimates of text skew angles on a large document image data set. The algorithm computes the optimal parameter settings on the fly without any human interaction. In this automatic mode, experimental results indicate that the algorithm generates estimated text skew angles within 0.5/spl deg/ of the true text skew angles with a probability of 99%. To process a 300 dpi document image, the algorithm takes 10 seconds on SUN Sparc 10 machines.
{"title":"Automatic text skew estimation in document images","authors":"Su S. Chen, R. Haralick, I. T. Phillips","doi":"10.1109/ICDAR.1995.602126","DOIUrl":"https://doi.org/10.1109/ICDAR.1995.602126","url":null,"abstract":"This paper describes an algorithm to estimate the text skew angle in a document image. The algorithm utilizes the recursive morphological transforms and yields accurate estimates of text skew angles on a large document image data set. The algorithm computes the optimal parameter settings on the fly without any human interaction. In this automatic mode, experimental results indicate that the algorithm generates estimated text skew angles within 0.5/spl deg/ of the true text skew angles with a probability of 99%. To process a 300 dpi document image, the algorithm takes 10 seconds on SUN Sparc 10 machines.","PeriodicalId":273519,"journal":{"name":"Proceedings of 3rd International Conference on Document Analysis and Recognition","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128912150","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：