Pub Date : 1997-08-18DOI: 10.1109/ICDAR.1997.619882
Y. Ariki, T. Teranishi
In accumulating and retrieving multimedia information such as images, speech and text, it is necessary to compress and retrieve the information efficiently and accurately. The purpose of this paper is to construct a multimedia database of TV news images based on telop character recognition. The first step is to detect telop frames and to segment the characters by differentiating the telop frames based on the fact that character regions have high brightness and the character edges are clear. The second step is the telop character recognition. It is performed by a subspace method using direction histogram features. The third step is indexing by extracting noun words after morphological analysis of the recognized telop characters. These noun words correspond with key words and are given to TV news articles as their indices. Finally TV news articles are classified into 10 topics such as politics, economics, culture, amusements, sports and so on based on the extracted indices. We employed an index-topic table to classify the articles using indices. The telop character recognition rate was 65.7% and the article classification rate was 67.3%.
{"title":"Indexing and classification of TV news articles based on telop recognition","authors":"Y. Ariki, T. Teranishi","doi":"10.1109/ICDAR.1997.619882","DOIUrl":"https://doi.org/10.1109/ICDAR.1997.619882","url":null,"abstract":"In accumulating and retrieving multimedia information such as images, speech and text, it is necessary to compress and retrieve the information efficiently and accurately. The purpose of this paper is to construct a multimedia database of TV news images based on telop character recognition. The first step is to detect telop frames and to segment the characters by differentiating the telop frames based on the fact that character regions have high brightness and the character edges are clear. The second step is the telop character recognition. It is performed by a subspace method using direction histogram features. The third step is indexing by extracting noun words after morphological analysis of the recognized telop characters. These noun words correspond with key words and are given to TV news articles as their indices. Finally TV news articles are classified into 10 topics such as politics, economics, culture, amusements, sports and so on based on the extracted indices. We employed an index-topic table to classify the articles using indices. The telop character recognition rate was 65.7% and the article classification rate was 67.3%.","PeriodicalId":435320,"journal":{"name":"Proceedings of the Fourth International Conference on Document Analysis and Recognition","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122875049","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 : 1997-08-18DOI: 10.1109/ICDAR.1997.620581
Yi-Hong Tseng, Chi-Chang Kuo, Hsi-Jian Lee
We present two techniques for speeding up character recognition. Our character recognition system, including the candidate cluster selection and detail matching modules, is implemented using two statistical features: crossing counts and contour direction counts. In the training stage, we divide characters into different clusters. To keep a very high recognition rate, the candidate cluster selection module selects the top 60 clusters with minimal distances from among 300 predefined clusters. To further speed up the recognition speed, we use a modified branch and bound algorithm in the detail matching module. In the automatic document reading system, characters and punctuation marks are first extracted from printed document images and sorted according to their positions and the document orientation. The system then recognizes all printed Chinese characters between pairs of punctuation marks. The results are then spoken aloud by a speech synthesis system.
{"title":"Speeding-up Chinese character recognition in an automatic document reading system","authors":"Yi-Hong Tseng, Chi-Chang Kuo, Hsi-Jian Lee","doi":"10.1109/ICDAR.1997.620581","DOIUrl":"https://doi.org/10.1109/ICDAR.1997.620581","url":null,"abstract":"We present two techniques for speeding up character recognition. Our character recognition system, including the candidate cluster selection and detail matching modules, is implemented using two statistical features: crossing counts and contour direction counts. In the training stage, we divide characters into different clusters. To keep a very high recognition rate, the candidate cluster selection module selects the top 60 clusters with minimal distances from among 300 predefined clusters. To further speed up the recognition speed, we use a modified branch and bound algorithm in the detail matching module. In the automatic document reading system, characters and punctuation marks are first extracted from printed document images and sorted according to their positions and the document orientation. The system then recognizes all printed Chinese characters between pairs of punctuation marks. The results are then spoken aloud by a speech synthesis system.","PeriodicalId":435320,"journal":{"name":"Proceedings of the Fourth International Conference on Document Analysis and Recognition","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125153129","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 : 1997-08-18DOI: 10.1109/ICDAR.1997.620600
Y. Yamazaki, N. Komatsu
We propose an on-line writer verification method to improve the reliability of verifying a specific system user. In the proposed method, a different text including ordinary characters is used on every verification process. This text can be selected automatically by the verification system so as to reflect the specific writer's features. A specific writer is accepted only when the same text, which is indicated by the verification system, is written, and the system can verify the writer's personal features from the written text. The proposed method makes it more difficult to disguise writer himself with forged handwriting data than the previous methods using only signatures.
{"title":"A proposal for a text-indicated writer verification method","authors":"Y. Yamazaki, N. Komatsu","doi":"10.1109/ICDAR.1997.620600","DOIUrl":"https://doi.org/10.1109/ICDAR.1997.620600","url":null,"abstract":"We propose an on-line writer verification method to improve the reliability of verifying a specific system user. In the proposed method, a different text including ordinary characters is used on every verification process. This text can be selected automatically by the verification system so as to reflect the specific writer's features. A specific writer is accepted only when the same text, which is indicated by the verification system, is written, and the system can verify the writer's personal features from the written text. The proposed method makes it more difficult to disguise writer himself with forged handwriting data than the previous methods using only signatures.","PeriodicalId":435320,"journal":{"name":"Proceedings of the Fourth International Conference on Document Analysis and Recognition","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125544272","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 : 1997-08-18DOI: 10.1109/ICDAR.1997.619809
Anil K. Jain, B. Yu
Transforming a paper document to its electronic version in a form suitable for efficient storage, retrieval and interpretation continues to be a challenging problem. An efficient document model is necessary to solve this problem. Document modeling involves techniques of thresholding, skew detection, geometric layout analysis and logical layout analysis. The derived model can then be used in document storage and retrieval. We use the traditional bottom-up approach based on the connected component extraction to efficiently implement page segmentation and region identification. A new document model which preserves top-down generation information is proposed based on which a document is logically represented for interactive editing, storage, retrieval, transfer and logical analysis.
{"title":"Page segmentation using document model","authors":"Anil K. Jain, B. Yu","doi":"10.1109/ICDAR.1997.619809","DOIUrl":"https://doi.org/10.1109/ICDAR.1997.619809","url":null,"abstract":"Transforming a paper document to its electronic version in a form suitable for efficient storage, retrieval and interpretation continues to be a challenging problem. An efficient document model is necessary to solve this problem. Document modeling involves techniques of thresholding, skew detection, geometric layout analysis and logical layout analysis. The derived model can then be used in document storage and retrieval. We use the traditional bottom-up approach based on the connected component extraction to efficiently implement page segmentation and region identification. A new document model which preserves top-down generation information is proposed based on which a document is logically represented for interactive editing, storage, retrieval, transfer and logical analysis.","PeriodicalId":435320,"journal":{"name":"Proceedings of the Fourth International Conference on Document Analysis and Recognition","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131097613","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 : 1997-08-18DOI: 10.1109/ICDAR.1997.619839
A. Amin, Seung-Gwon Kim, C. Sammut
Recognition of Chinese characters has been an area of great interest for many years, and a large number of research papers and reports have already been published in this area. There are several major problems with Chinese character recognition: Chinese characters are distinct and ideographic, the character size is very large and a lot of structurally similar characters exist in the character set. Thus, classification criteria are difficult to generate. This paper presents a new technique for the recognition of hand-printed Chinese characters using machine learning C4.5. Conventional methods have relied on hand-constructed dictionaries which are tedious to construct and difficult to make tolerant to variation in writing styles. The paper also discusses Chinese character recognition using dominant point feature extraction and C4.5. The system was tested with 900 characters (each character has 40 samples) and the rate of recognition obtained was 84%.
{"title":"Hand-printed Chinese character recognition via machine learning","authors":"A. Amin, Seung-Gwon Kim, C. Sammut","doi":"10.1109/ICDAR.1997.619839","DOIUrl":"https://doi.org/10.1109/ICDAR.1997.619839","url":null,"abstract":"Recognition of Chinese characters has been an area of great interest for many years, and a large number of research papers and reports have already been published in this area. There are several major problems with Chinese character recognition: Chinese characters are distinct and ideographic, the character size is very large and a lot of structurally similar characters exist in the character set. Thus, classification criteria are difficult to generate. This paper presents a new technique for the recognition of hand-printed Chinese characters using machine learning C4.5. Conventional methods have relied on hand-constructed dictionaries which are tedious to construct and difficult to make tolerant to variation in writing styles. The paper also discusses Chinese character recognition using dominant point feature extraction and C4.5. The system was tested with 900 characters (each character has 40 samples) and the rate of recognition obtained was 84%.","PeriodicalId":435320,"journal":{"name":"Proceedings of the Fourth International Conference on Document Analysis and Recognition","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130141079","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 : 1997-08-18DOI: 10.1109/ICDAR.1997.620570
Chiu L. Yu, C. Suen, Y. Tang
This paper describes a Chinese cheque processing system currently under development at the Centre for Pattern Recognition and Machine Intelligence (CENPARMI). The information on Chinese bank cheques is not the same as that on alphanumeric bank cheques. The legal amount in a Chinese bank cheque is the Chinese character text associated with each currency unit. This paper discusses a technique using each currency unit as a key word to locate/extract the legal amount in bank cheques. In the analysis and recognition process, the system tries to locate the smallest currency units in the image and identifies it first. Then, the system tries to locate the image strings associated with each currency unit. Each image string is separated and recognized. Next, a set of rules and context are applied to recognize the characters. In order to choose the correct one, the recognized character string is accepted only if it satisfies all the conditions governed by rules.
{"title":"Location and recognition of legal amounts on Chinese bank cheques","authors":"Chiu L. Yu, C. Suen, Y. Tang","doi":"10.1109/ICDAR.1997.620570","DOIUrl":"https://doi.org/10.1109/ICDAR.1997.620570","url":null,"abstract":"This paper describes a Chinese cheque processing system currently under development at the Centre for Pattern Recognition and Machine Intelligence (CENPARMI). The information on Chinese bank cheques is not the same as that on alphanumeric bank cheques. The legal amount in a Chinese bank cheque is the Chinese character text associated with each currency unit. This paper discusses a technique using each currency unit as a key word to locate/extract the legal amount in bank cheques. In the analysis and recognition process, the system tries to locate the smallest currency units in the image and identifies it first. Then, the system tries to locate the image strings associated with each currency unit. Each image string is separated and recognized. Next, a set of rules and context are applied to recognize the characters. In order to choose the correct one, the recognized character string is accepted only if it satisfies all the conditions governed by rules.","PeriodicalId":435320,"journal":{"name":"Proceedings of the Fourth International Conference on Document Analysis and Recognition","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128675433","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 : 1997-08-18DOI: 10.1109/ICDAR.1997.619863
D. Doermann, Huiping Li, O. Kia
We propose and implement a method for detecting duplicate documents in very large image databases. The method is based on a robust "signature" extracted from each document image which is used to index into a table of previously processed documents. The approach has a number of advantages over OCR or other recognition based methods, including speed and robustness to imaging distortions. To justify the approach and test the scalability, we have developed a simulator which allows us to change parameters of the system and examine performance for millions of document signatures. A complete system is implemented and tested on a test collection of technical articles and memos.
{"title":"The detection of duplicates in document image databases","authors":"D. Doermann, Huiping Li, O. Kia","doi":"10.1109/ICDAR.1997.619863","DOIUrl":"https://doi.org/10.1109/ICDAR.1997.619863","url":null,"abstract":"We propose and implement a method for detecting duplicate documents in very large image databases. The method is based on a robust \"signature\" extracted from each document image which is used to index into a table of previously processed documents. The approach has a number of advantages over OCR or other recognition based methods, including speed and robustness to imaging distortions. To justify the approach and test the scalability, we have developed a simulator which allows us to change parameters of the system and examine performance for millions of document signatures. A complete system is implemented and tested on a test collection of technical articles and memos.","PeriodicalId":435320,"journal":{"name":"Proceedings of the Fourth International Conference on Document Analysis and Recognition","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116323500","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 : 1997-08-18DOI: 10.1109/ICDAR.1997.619853
Christiane Schmidt, K. Kraiss
The paper presents a novel method of on-line signature verification that analyzes both the shape of the signature and dynamics of the writing process. This approach automatically determines characteristic features of the written image and combines these shape features with features from the writing dynamics. For establishing a writing characteristic template for one signer the signature is separated into characteristic segments. The segmentation algorithm extracts writing points which would give a forgery the appearance of the original. For these significant points local extreme values, which identify writing segments, are calculated. Subsequently, dynamic features are computed for the segments. The developed system needs three signatures of one person for the establishment of a personalized template. A database has been collected with 544 signatures of 27 signers for evaluation. The developed system achieved a correct acceptance rate of 78% and a correct rejection rate of 100%.
{"title":"Establishment of personalized templates for automatic signature verification","authors":"Christiane Schmidt, K. Kraiss","doi":"10.1109/ICDAR.1997.619853","DOIUrl":"https://doi.org/10.1109/ICDAR.1997.619853","url":null,"abstract":"The paper presents a novel method of on-line signature verification that analyzes both the shape of the signature and dynamics of the writing process. This approach automatically determines characteristic features of the written image and combines these shape features with features from the writing dynamics. For establishing a writing characteristic template for one signer the signature is separated into characteristic segments. The segmentation algorithm extracts writing points which would give a forgery the appearance of the original. For these significant points local extreme values, which identify writing segments, are calculated. Subsequently, dynamic features are computed for the segments. The developed system needs three signatures of one person for the establishment of a personalized template. A database has been collected with 544 signatures of 27 signers for evaluation. The developed system achieved a correct acceptance rate of 78% and a correct rejection rate of 100%.","PeriodicalId":435320,"journal":{"name":"Proceedings of the Fourth International Conference on Document Analysis and Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131146447","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 : 1997-08-18DOI: 10.1109/ICDAR.1997.620548
T. Yamauchi, Y. Itamoto, J. Tsukumo
Character recognition using multi-template methods is promising. Higher classification performance can be achieved according to an increase in the number of templates. However, classification performance is saturated because there is classifiability loss in feature extraction. The paper proposes a new multi-template method which learns training patterns with character shape information assigned by the authors. This method uses contour feature and direction feature, and includes a character shape consistency test applied to the conventional multi-template methods. The paper presents experimental results obtained from handprinted numerals. On the ETL-6 database classification experiment the classification rate was 99.19% and the substitution rate was 0.03%. A higher classification rate could be achieved.
{"title":"Shape based learning for a multi-template method, and its application to handprinted numeral recognition","authors":"T. Yamauchi, Y. Itamoto, J. Tsukumo","doi":"10.1109/ICDAR.1997.620548","DOIUrl":"https://doi.org/10.1109/ICDAR.1997.620548","url":null,"abstract":"Character recognition using multi-template methods is promising. Higher classification performance can be achieved according to an increase in the number of templates. However, classification performance is saturated because there is classifiability loss in feature extraction. The paper proposes a new multi-template method which learns training patterns with character shape information assigned by the authors. This method uses contour feature and direction feature, and includes a character shape consistency test applied to the conventional multi-template methods. The paper presents experimental results obtained from handprinted numerals. On the ETL-6 database classification experiment the classification rate was 99.19% and the substitution rate was 0.03%. A higher classification rate could be achieved.","PeriodicalId":435320,"journal":{"name":"Proceedings of the Fourth International Conference on Document Analysis and Recognition","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128343694","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 : 1997-08-18DOI: 10.1109/ICDAR.1997.620558
S. Naoi, Maki Yabuki
The global interpolation method we propose can extract a handwritten alpha-numeric character pattern even if it overlaps a border. Our method interpolates blank segments in a character after borders are removed by globally evaluating segment label connectivity and connectedness to produce characters with smooth edges. However, the method cannot interpolate missing superpositioning segments, such as an overlapping horizontal line in the number "2". To solve this problem, we propose a global interpolation method II which adds top-down recognition processing to the bottom-up processing of the existing global interpolation method by automatically acquiring knowledge of the relationship between the overlapped condition and recognition reliability. Experimental results which use generated overlapping characters using the ETL database showed that our global interpolation method II has almost the same accuracy as the original ETL database.
{"title":"Global interpolation method II for handwritten numbers overlapping a border by automatic knowledge acquisition of overlapped conditions","authors":"S. Naoi, Maki Yabuki","doi":"10.1109/ICDAR.1997.620558","DOIUrl":"https://doi.org/10.1109/ICDAR.1997.620558","url":null,"abstract":"The global interpolation method we propose can extract a handwritten alpha-numeric character pattern even if it overlaps a border. Our method interpolates blank segments in a character after borders are removed by globally evaluating segment label connectivity and connectedness to produce characters with smooth edges. However, the method cannot interpolate missing superpositioning segments, such as an overlapping horizontal line in the number \"2\". To solve this problem, we propose a global interpolation method II which adds top-down recognition processing to the bottom-up processing of the existing global interpolation method by automatically acquiring knowledge of the relationship between the overlapped condition and recognition reliability. Experimental results which use generated overlapping characters using the ETL database showed that our global interpolation method II has almost the same accuracy as the original ETL database.","PeriodicalId":435320,"journal":{"name":"Proceedings of the Fourth International Conference on Document Analysis and Recognition","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133000117","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：