Pub Date : 2002-08-06DOI: 10.1109/IWFHR.2002.1030956
M. Pechwitz, V. Märgner
Baseline information has been used for diverse purposes in handwriting research. The baseline represents a first orientation in a word and it is often a precondition for subsequent algorithms, including preprocessing tasks, segmentation and feature extraction for recognition systems. Approaches based on the horizontal projection histogram are used for Arabic printed text but they are ill-suited for Arabic handwritten words. In this paper we present a method that is completely based on polygonally approximated skeleton processing. The central algorithm is concerned with finding features in the skeleton and processing linear regression analysis. Our method performs very well as long as the model assumption of one straight line applies. We tested the method on 26459 isolated Tunisian town names written by 411 writers (IFNIENIT-database).
{"title":"Baseline estimation for Arabic handwritten words","authors":"M. Pechwitz, V. Märgner","doi":"10.1109/IWFHR.2002.1030956","DOIUrl":"https://doi.org/10.1109/IWFHR.2002.1030956","url":null,"abstract":"Baseline information has been used for diverse purposes in handwriting research. The baseline represents a first orientation in a word and it is often a precondition for subsequent algorithms, including preprocessing tasks, segmentation and feature extraction for recognition systems. Approaches based on the horizontal projection histogram are used for Arabic printed text but they are ill-suited for Arabic handwritten words. In this paper we present a method that is completely based on polygonally approximated skeleton processing. The central algorithm is concerned with finding features in the skeleton and processing linear regression analysis. Our method performs very well as long as the model assumption of one straight line applies. We tested the method on 26459 isolated Tunisian town names written by 411 writers (IFNIENIT-database).","PeriodicalId":114017,"journal":{"name":"Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130705183","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 : 2002-08-06DOI: 10.1109/IWFHR.2002.1030923
S. Srihari, Sangjik Lee
A handwriting recognition technique and a handwriting identification technique were combined and applied on anthrax-related handwritten mail. The HWAI (handwritten address interpretation) system interprets the address on the anthrax-related letters. The HWAI process can be modified to provide specific alphabet images which can then be used for writer identification. Micro-level feature values from segmented characters were extracted and an identification test was conducted. Preliminary results based on automatic handwriting recognition and identification are shown.
{"title":"Automatic handwriting recognition and writer matching on anthrax-related handwritten mail","authors":"S. Srihari, Sangjik Lee","doi":"10.1109/IWFHR.2002.1030923","DOIUrl":"https://doi.org/10.1109/IWFHR.2002.1030923","url":null,"abstract":"A handwriting recognition technique and a handwriting identification technique were combined and applied on anthrax-related handwritten mail. The HWAI (handwritten address interpretation) system interprets the address on the anthrax-related letters. The HWAI process can be modified to provide specific alphabet images which can then be used for writer identification. Micro-level feature values from segmented characters were extracted and an identification test was conducted. Preliminary results based on automatic handwriting recognition and identification are shown.","PeriodicalId":114017,"journal":{"name":"Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134189400","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 : 2002-08-06DOI: 10.1109/IWFHR.2002.1030879
S. Marukatat, T. Artières, P. Gallinari, B. Dorizzi
In this paper we study the use of confidence measures for an on-line handwriting recognizer. We investigate various confidence measures and their integration in an isolated word recognition system as well as in a sentence recognition system. In isolated word recognition tasks, the rejection mechanism is designed in order to reject the outputs of the recognizer that are possibly wrong, which is the case for badly written words, out-of-vocabulary words or general drawing. In sentence recognition tasks, the rejection mechanism allows rejecting parts of the decoded sentence.
{"title":"Rejection measures for handwriting sentence recognition","authors":"S. Marukatat, T. Artières, P. Gallinari, B. Dorizzi","doi":"10.1109/IWFHR.2002.1030879","DOIUrl":"https://doi.org/10.1109/IWFHR.2002.1030879","url":null,"abstract":"In this paper we study the use of confidence measures for an on-line handwriting recognizer. We investigate various confidence measures and their integration in an isolated word recognition system as well as in a sentence recognition system. In isolated word recognition tasks, the rejection mechanism is designed in order to reject the outputs of the recognizer that are possibly wrong, which is the case for badly written words, out-of-vocabulary words or general drawing. In sentence recognition tasks, the rejection mechanism allows rejecting parts of the decoded sentence.","PeriodicalId":114017,"journal":{"name":"Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132913036","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 : 2002-08-06DOI: 10.1109/IWFHR.2002.1030953
T. Sari, M. Sellami
In this paper we present a contextual-based method for correcting Arabic words generated by OCR systems. This technique operates as a post-processor and it wants to be universal. It corrects substitution and rejection errors. The Arabic language properties are very useful in morpho-lexical analysis and therefore they are strongly exploited in the development of the method. The substitution errors, the most frequently committed ones by the OCR systems, are rewritten in production rules to be used by a rule-based system for correcting Arabic words. The first version of the developed method operates only at the morpho-lexical level, the extension to the other levels of language analysis is considered in perspectives.
{"title":"MOrpho-LEXical analysis for correcting OCR-generated Arabic words (MOLEX)","authors":"T. Sari, M. Sellami","doi":"10.1109/IWFHR.2002.1030953","DOIUrl":"https://doi.org/10.1109/IWFHR.2002.1030953","url":null,"abstract":"In this paper we present a contextual-based method for correcting Arabic words generated by OCR systems. This technique operates as a post-processor and it wants to be universal. It corrects substitution and rejection errors. The Arabic language properties are very useful in morpho-lexical analysis and therefore they are strongly exploited in the development of the method. The substitution errors, the most frequently committed ones by the OCR systems, are rewritten in production rules to be used by a rule-based system for correcting Arabic words. The first version of the developed method operates only at the morpho-lexical level, the extension to the other levels of language analysis is considered in perspectives.","PeriodicalId":114017,"journal":{"name":"Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116517719","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 : 2002-08-06DOI: 10.1109/IWFHR.2002.1030962
M. Shridhar, F. Kimura, Bart Truijen, G. Houle
Significant progress has been achieved in recognition of handwritten words during the past five years. Cursive recognition is currently used in real-live systems for applications such as check, giro, generic form, and address processing. Common to these applications is the use of lexicon. This paper addresses the issues of lexicon completeness and its impact on accuracy (rejection and error rates). It has been documented in several address recognition studies that recognition accuracy falls off as the size of the lexicon increases. However, the error-rejection performance of word recognition, when the available lexicon is only partially complete has not been thoroughly analyzed.
{"title":"Impact of lexicon completeness on city name recognition","authors":"M. Shridhar, F. Kimura, Bart Truijen, G. Houle","doi":"10.1109/IWFHR.2002.1030962","DOIUrl":"https://doi.org/10.1109/IWFHR.2002.1030962","url":null,"abstract":"Significant progress has been achieved in recognition of handwritten words during the past five years. Cursive recognition is currently used in real-live systems for applications such as check, giro, generic form, and address processing. Common to these applications is the use of lexicon. This paper addresses the issues of lexicon completeness and its impact on accuracy (rejection and error rates). It has been documented in several address recognition studies that recognition accuracy falls off as the size of the lexicon increases. However, the error-rejection performance of word recognition, when the available lexicon is only partially complete has not been thoroughly analyzed.","PeriodicalId":114017,"journal":{"name":"Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132119545","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 : 2002-08-06DOI: 10.1109/IWFHR.2002.1030889
Stefan Jäger, M. Nakagawa, Cheng-Lin Liu
Recognizers supporting multiple languages and writing systems are becoming increasingly important due to the international success of pen-based systems. The main intention of the paper is to improve our understanding of the differences and similarities between Japanese and western handwriting recognition. Knowing the common techniques is important for developing compact and powerful multi-language recognizers with integrated modules for both writing systems. In particular, the simultaneous recognition of western and Japanese handwriting in multi-language documents requires methods suitable for both writing systems. Though the Japanese and western writing systems are completely different, we present many similar recognition techniques facilitating an integration of processing steps.
{"title":"Comparing on-line recognition of Japanese and western script in preparation for recognizing multi-language documents","authors":"Stefan Jäger, M. Nakagawa, Cheng-Lin Liu","doi":"10.1109/IWFHR.2002.1030889","DOIUrl":"https://doi.org/10.1109/IWFHR.2002.1030889","url":null,"abstract":"Recognizers supporting multiple languages and writing systems are becoming increasingly important due to the international success of pen-based systems. The main intention of the paper is to improve our understanding of the differences and similarities between Japanese and western handwriting recognition. Knowing the common techniques is important for developing compact and powerful multi-language recognizers with integrated modules for both writing systems. In particular, the simultaneous recognition of western and Japanese handwriting in multi-language documents requires methods suitable for both writing systems. Though the Japanese and western writing systems are completely different, we present many similar recognition techniques facilitating an integration of processing steps.","PeriodicalId":114017,"journal":{"name":"Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133972976","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 : 2002-08-06DOI: 10.1109/IWFHR.2002.1030931
Ho-Sub Yoon, Jae-Heum Lee, Haesik Yang
In this paper, we propose a method of online signature verification system using HMM models in a polar coordinate system. In the previous works, the signature verification was performed in terms of a standard X-Y coordinate system. This coordinate system always needs the normalization of signature stroke size and angle variance. To reduce normalization error and computing time, we propose the polar coordinate system. Under the polar coordinate system, the feature sets are robust and independent of size and angle variation according to the user characteristics. The use of HMMs instead of a traditional Euclidian distance metric for the determination of the degree of match between a test signature and a reference signature model brings about a significant improvement in performance as it permits the incorporation of heuristics. The experiments shows that the proposed method gives lower equal error rate 2.2% from 50,000 testing cases.
{"title":"An online signature verification system using hidden Markov model in polar space","authors":"Ho-Sub Yoon, Jae-Heum Lee, Haesik Yang","doi":"10.1109/IWFHR.2002.1030931","DOIUrl":"https://doi.org/10.1109/IWFHR.2002.1030931","url":null,"abstract":"In this paper, we propose a method of online signature verification system using HMM models in a polar coordinate system. In the previous works, the signature verification was performed in terms of a standard X-Y coordinate system. This coordinate system always needs the normalization of signature stroke size and angle variance. To reduce normalization error and computing time, we propose the polar coordinate system. Under the polar coordinate system, the feature sets are robust and independent of size and angle variation according to the user characteristics. The use of HMMs instead of a traditional Euclidian distance metric for the determination of the degree of match between a test signature and a reference signature model brings about a significant improvement in performance as it permits the incorporation of heuristics. The experiments shows that the proposed method gives lower equal error rate 2.2% from 50,000 testing cases.","PeriodicalId":114017,"journal":{"name":"Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116600566","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 : 2002-08-06DOI: 10.1109/IWFHR.2002.1030949
A. Seropian, N. Vincent
In this paper we propose a new approach that allows authenticating a writer. To achieve this goal the autosimilarity properties in writings are used, that is to say we are extracting some invariant pieces of the writing, invariant patterns that are characterizing the texts of a writer. From a practical point of view, these invariant shapes are determined by adaptation of techniques that have been developed in the fractal compression process. During a learning phase the invariant patterns are extracted and in a second step they are used as a reference base in order to analyze an unknown writing. The results of the analysis are quantified by measurement of the quality of a compression/decompression process elaborated using the reference base associated with different.
{"title":"Writers authentication and fractal compression","authors":"A. Seropian, N. Vincent","doi":"10.1109/IWFHR.2002.1030949","DOIUrl":"https://doi.org/10.1109/IWFHR.2002.1030949","url":null,"abstract":"In this paper we propose a new approach that allows authenticating a writer. To achieve this goal the autosimilarity properties in writings are used, that is to say we are extracting some invariant pieces of the writing, invariant patterns that are characterizing the texts of a writer. From a practical point of view, these invariant shapes are determined by adaptation of techniques that have been developed in the fractal compression process. During a learning phase the invariant patterns are extracted and in a second step they are used as a reference base in order to analyze an unknown writing. The results of the analysis are quantified by measurement of the quality of a compression/decompression process elaborated using the reference base associated with different.","PeriodicalId":114017,"journal":{"name":"Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123626053","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 : 2002-08-06DOI: 10.1109/IWFHR.2002.1030936
A. Brakensiek, J. Rottland, G. Rigoll
In this paper a recognition system, based on tied-mixture hidden Markov models, for handwritten address words is described, which makes use of a language model that consists of backoff character n-grams. For a dictionary-based recognition system it is essential that the structure of the address (name, street, city) is known. If the single parts of the address cannot be categorized, the used vocabulary is unknown and thus unlimited. The performance of this open vocabulary recognition using n-grams is compared to the use of dictionaries of different sizes. Especially, the confidence of recognition results and the possibility of a useful post-processing are significant advantages of language models.
{"title":"Handwritten address recognition with open vocabulary using character n-grams","authors":"A. Brakensiek, J. Rottland, G. Rigoll","doi":"10.1109/IWFHR.2002.1030936","DOIUrl":"https://doi.org/10.1109/IWFHR.2002.1030936","url":null,"abstract":"In this paper a recognition system, based on tied-mixture hidden Markov models, for handwritten address words is described, which makes use of a language model that consists of backoff character n-grams. For a dictionary-based recognition system it is essential that the structure of the address (name, street, city) is known. If the single parts of the address cannot be categorized, the used vocabulary is unknown and thus unlimited. The performance of this open vocabulary recognition using n-grams is compared to the use of dictionaries of different sizes. Especially, the confidence of recognition results and the possibility of a useful post-processing are significant advantages of language models.","PeriodicalId":114017,"journal":{"name":"Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130176256","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 : 2002-08-06DOI: 10.1109/IWFHR.2002.1030921
K. Franke, Ottmar Bünnemeyer, T. Sy
This paper presents an approach for ink type recognition. Ink type classes will be derived from the physical properties of ink. Ink specific trace morphologies are considered as textures. From these discriminant texture features of the co-occurrence matrix will be derived. The proposed method for automated ink type recognition was tested using 62 different kinds of pens and refills. The achieved recognition result of 99.7% for 600 dpi and 98.4% for 300 dpi handwritings further promotes the study of trace morphologies in particular for application in forensic writer identification.
{"title":"Ink texture analysis for writer identification","authors":"K. Franke, Ottmar Bünnemeyer, T. Sy","doi":"10.1109/IWFHR.2002.1030921","DOIUrl":"https://doi.org/10.1109/IWFHR.2002.1030921","url":null,"abstract":"This paper presents an approach for ink type recognition. Ink type classes will be derived from the physical properties of ink. Ink specific trace morphologies are considered as textures. From these discriminant texture features of the co-occurrence matrix will be derived. The proposed method for automated ink type recognition was tested using 62 different kinds of pens and refills. The achieved recognition result of 99.7% for 600 dpi and 98.4% for 300 dpi handwritings further promotes the study of trace morphologies in particular for application in forensic writer identification.","PeriodicalId":114017,"journal":{"name":"Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127192389","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：