Pub Date : 2002-08-06DOI: 10.1109/IWFHR.2002.1030896
Wenwei Wang, A. Brakensiek, G. Rigoll
Due to large shape variations in human handwriting, recognition accuracy of cursive handwritten word is hardly satisfying using a single classifier. In this paper we introduce a framework to combine results of multiple classifiers and present an intuitive run-time weighted opinion pool combination approach for recognizing cursive handwritten words with a large size vocabulary. The individual classifiers are evaluated run-time dynamically. The final combination is weighted according to their local performance. For an open vocabulary recognition task, we use the ROVER algorithm to combine the different strings of characters provided by each classifier. Experimental results for recognizing cursive handwritten words demonstrate that our new approach achieves better recognition performance and reduces the relative error rate significantly.
{"title":"Combination of multiple classifiers for handwritten word recognition","authors":"Wenwei Wang, A. Brakensiek, G. Rigoll","doi":"10.1109/IWFHR.2002.1030896","DOIUrl":"https://doi.org/10.1109/IWFHR.2002.1030896","url":null,"abstract":"Due to large shape variations in human handwriting, recognition accuracy of cursive handwritten word is hardly satisfying using a single classifier. In this paper we introduce a framework to combine results of multiple classifiers and present an intuitive run-time weighted opinion pool combination approach for recognizing cursive handwritten words with a large size vocabulary. The individual classifiers are evaluated run-time dynamically. The final combination is weighted according to their local performance. For an open vocabulary recognition task, we use the ROVER algorithm to combine the different strings of characters provided by each classifier. Experimental results for recognizing cursive handwritten words demonstrate that our new approach achieves better recognition performance and reduces the relative error rate significantly.","PeriodicalId":114017,"journal":{"name":"Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition","volume":"223 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":"114469821","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.2002.1030904
Naomi Iwayama, K. Akiyama, K. Ishigaki
We propose a new method of adaptation in online handwritten character recognition. The method, called the "hybrid adaptation", integrates adaptive classification with adaptive context processing. Hybrid adaptation includes a mechanism that minimizes the negative effects of adaptation that might be caused by the integration. Online handwritten character recognition software with hybrid adaptation can be loaded on terminals having low memory capacity since our implementation of both adaptive classification and adaptive context processing does not require much memory. In our experiments, under the condition that all input strings had been input previously, the first-hit rate of hybrid adaptation was 99.0%, while that of non-adaptation was 93.3%, that of adaptive classification was 95.3% and that of adaptive context processing was 97.9%. In addition, we confirm that hybrid adaptation could enhance the level of satisfaction of the individual user.
{"title":"Hybrid adaptation: integration of adaptive classification with adaptive context processing","authors":"Naomi Iwayama, K. Akiyama, K. Ishigaki","doi":"10.1109/IWFHR.2002.1030904","DOIUrl":"https://doi.org/10.1109/IWFHR.2002.1030904","url":null,"abstract":"We propose a new method of adaptation in online handwritten character recognition. The method, called the \"hybrid adaptation\", integrates adaptive classification with adaptive context processing. Hybrid adaptation includes a mechanism that minimizes the negative effects of adaptation that might be caused by the integration. Online handwritten character recognition software with hybrid adaptation can be loaded on terminals having low memory capacity since our implementation of both adaptive classification and adaptive context processing does not require much memory. In our experiments, under the condition that all input strings had been input previously, the first-hit rate of hybrid adaptation was 99.0%, while that of non-adaptation was 93.3%, that of adaptive classification was 95.3% and that of adaptive context processing was 97.9%. In addition, we confirm that hybrid adaptation could enhance the level of satisfaction of the individual user.","PeriodicalId":114017,"journal":{"name":"Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition","volume":"16 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":"125114126","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.2002.1030907
F. Rahman, M. Fairhurst, Sanaul Hoque
Classifier combination and the design of multiple expert decision combination strategies are now considered to be very important issues in pattern recognition. This paper describes an investigation covering two important aspects of decision combination: optimization and generality.
{"title":"Novel approaches to optimized self-configuration in high performance multiple-expert classifiers","authors":"F. Rahman, M. Fairhurst, Sanaul Hoque","doi":"10.1109/IWFHR.2002.1030907","DOIUrl":"https://doi.org/10.1109/IWFHR.2002.1030907","url":null,"abstract":"Classifier combination and the design of multiple expert decision combination strategies are now considered to be very important issues in pattern recognition. This paper describes an investigation covering two important aspects of decision combination: optimization and generality.","PeriodicalId":114017,"journal":{"name":"Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition","volume":"53 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":"115528534","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.2002.1030959
Kalyan Takru, G. Leedham
This paper reports on a novel technique for the separation of characters and words that are connected through touching or overlapping of characters between adjacent lines of text. The technique employs structural knowledge of handwriting styles where overlap is most frequently observed. The method is shown to work well in the most usual cases and resolve many of the more difficult cases observed in very poor quality handwritten documents.
{"title":"Separation of touching and overlapping words in adjacent lines of handwritten text","authors":"Kalyan Takru, G. Leedham","doi":"10.1109/IWFHR.2002.1030959","DOIUrl":"https://doi.org/10.1109/IWFHR.2002.1030959","url":null,"abstract":"This paper reports on a novel technique for the separation of characters and words that are connected through touching or overlapping of characters between adjacent lines of text. The technique employs structural knowledge of handwriting styles where overlap is most frequently observed. The method is shown to work well in the most usual cases and resolve many of the more difficult cases observed in very poor quality handwritten documents.","PeriodicalId":114017,"journal":{"name":"Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition","volume":"85 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":"115657566","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.2002.1030952
T. Sari, L. Souici-Meslati, M. Sellami
Character segmentation is a necessary preprocessing step for character recognition in many OCR systems. It is an important step because incorrectly segmented characters are unlikely to be recognized correctly. The most difficult case in character segmentation is the cursive script. The scripted nature of Arabic written language poses some high challenges for automatic character segmentation and recognition. In this paper, a new character segmentation algorithm (ACSA) of Arabic scripts is presented. The developed segmentation algorithm yields on the segmentation of isolated handwritten words in perfectly separated characters. It is based on morphological rules, which are constructed at the feature extraction phase. Finally, ACSA is combined with an existing handwritten Arabic character recognition system (RECAM).
{"title":"Off-line handwritten Arabic character segmentation algorithm: ACSA","authors":"T. Sari, L. Souici-Meslati, M. Sellami","doi":"10.1109/IWFHR.2002.1030952","DOIUrl":"https://doi.org/10.1109/IWFHR.2002.1030952","url":null,"abstract":"Character segmentation is a necessary preprocessing step for character recognition in many OCR systems. It is an important step because incorrectly segmented characters are unlikely to be recognized correctly. The most difficult case in character segmentation is the cursive script. The scripted nature of Arabic written language poses some high challenges for automatic character segmentation and recognition. In this paper, a new character segmentation algorithm (ACSA) of Arabic scripts is presented. The developed segmentation algorithm yields on the segmentation of isolated handwritten words in perfectly separated characters. It is based on morphological rules, which are constructed at the feature extraction phase. Finally, ACSA is combined with an existing handwritten Arabic character recognition system (RECAM).","PeriodicalId":114017,"journal":{"name":"Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition","volume":"12 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":"126912343","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.2002.1030947
R. Kashi, W. Nelson
This method describes the advantages of a signature verification or any other biometric methodology having multiple tries. Traditional verification techniques acquire a test sample and compare with a model and a decision is made as to whether the test sample is genuine or a forgery. While it is clear that allowing a second try will reduce the false rejects, it will also increase the false accepts. However, from our experiments, the increase in false accepts was small compared to the dramatic reduction in false rejects. At the 1% false rejection (FR) rate, the addition of the second try reduced the false acceptance (FA) rate from 4.7% to 1.3%. So, in applications where very low FR is required, allowing the signer a second try appears to be a good option.
{"title":"Signature verification: benefits of multiple tries","authors":"R. Kashi, W. Nelson","doi":"10.1109/IWFHR.2002.1030947","DOIUrl":"https://doi.org/10.1109/IWFHR.2002.1030947","url":null,"abstract":"This method describes the advantages of a signature verification or any other biometric methodology having multiple tries. Traditional verification techniques acquire a test sample and compare with a model and a decision is made as to whether the test sample is genuine or a forgery. While it is clear that allowing a second try will reduce the false rejects, it will also increase the false accepts. However, from our experiments, the increase in false accepts was small compared to the dramatic reduction in false rejects. At the 1% false rejection (FR) rate, the addition of the second try reduced the false acceptance (FA) rate from 4.7% to 1.3%. So, in applications where very low FR is required, allowing the signer a second try appears to be a good option.","PeriodicalId":114017,"journal":{"name":"Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition","volume":"163 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":"127380499","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.2002.1030910
Sanaul Hoque, K. Sirlantzis, M. Fairhurst
This paper describes a multiple classifier configuration for high performance off-line handwritten character recognition applications. Along with a conventional scanning n-tuple classifier (or sn-tuple) implementation, three other sn-tuple systems have been used which are trained using a binary feature set extracted from the contour chain-codes using a novel decomposition technique. The overall accuracy thus achievable by the proposed scheme is much higher than most other classification systems available and the added complexity (over conventional sn-tuple system) is minimal.
{"title":"Bit plane decomposition and the scanning n-tuple classifier","authors":"Sanaul Hoque, K. Sirlantzis, M. Fairhurst","doi":"10.1109/IWFHR.2002.1030910","DOIUrl":"https://doi.org/10.1109/IWFHR.2002.1030910","url":null,"abstract":"This paper describes a multiple classifier configuration for high performance off-line handwritten character recognition applications. Along with a conventional scanning n-tuple classifier (or sn-tuple) implementation, three other sn-tuple systems have been used which are trained using a binary feature set extracted from the contour chain-codes using a novel decomposition technique. The overall accuracy thus achievable by the proposed scheme is much higher than most other classification systems available and the added complexity (over conventional sn-tuple system) is minimal.","PeriodicalId":114017,"journal":{"name":"Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition","volume":"16 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":"127974795","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.2002.1030944
Teruyuki Yamaguchi, S. Tsuruoka, T. Yoshikawa, T. Shinogi, Eiji Makimoto, Hisao Ogata, M. Shridhar
The present character recognition system needs the segmentation process as preprocessing for an input image of the touching character string. The process divides it into some isolated characters. To improve the total performance of the character recognition system, it is required to lessen the number of retrieval path in the candidate character lattice. We proposed the segmentation method based on connecting condition of the neighbor lines to resolve these problems in the previous paper. In this paper, we modify, our segmentation algorithm, and we evaluate the performance of these segmentation methods by a direct evaluation system with permissible degree and an indirect evaluation using the character recognition. We confirm the usefulness of our new method for 456 touching handwritten Japanese "Kanji" image with 948 characters by the comparison of three segmentation methods. The correct segmentation rates are 61.4% (conventional method), 75.1% (previous method), and 83.0% (proposed method).
{"title":"A segmentation system for touching handwritten Japanese characters","authors":"Teruyuki Yamaguchi, S. Tsuruoka, T. Yoshikawa, T. Shinogi, Eiji Makimoto, Hisao Ogata, M. Shridhar","doi":"10.1109/IWFHR.2002.1030944","DOIUrl":"https://doi.org/10.1109/IWFHR.2002.1030944","url":null,"abstract":"The present character recognition system needs the segmentation process as preprocessing for an input image of the touching character string. The process divides it into some isolated characters. To improve the total performance of the character recognition system, it is required to lessen the number of retrieval path in the candidate character lattice. We proposed the segmentation method based on connecting condition of the neighbor lines to resolve these problems in the previous paper. In this paper, we modify, our segmentation algorithm, and we evaluate the performance of these segmentation methods by a direct evaluation system with permissible degree and an indirect evaluation using the character recognition. We confirm the usefulness of our new method for 456 touching handwritten Japanese \"Kanji\" image with 948 characters by the comparison of three segmentation methods. The correct segmentation rates are 61.4% (conventional method), 75.1% (previous method), and 83.0% (proposed method).","PeriodicalId":114017,"journal":{"name":"Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition","volume":"12 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":"127627701","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.2002.1030945
C. Tomai, Bin Zhang, Venu Govindaraju
There is a large number of scanned historical documents that need to be indexed for archival and retrieval purposes. A visual word spotting scheme that would serve these purposes is a challenging task even when the transcription of the document image is available. We propose a framework for mapping each word in the transcript to the associated word image in the document. Coarse word mapping based on document constraints is used for lexicon reduction. Then, word mappings are refined using word recognition results by a dynamic programming algorithm that finds the best match while satisfying the constraints.
{"title":"Transcript mapping for historic handwritten document images","authors":"C. Tomai, Bin Zhang, Venu Govindaraju","doi":"10.1109/IWFHR.2002.1030945","DOIUrl":"https://doi.org/10.1109/IWFHR.2002.1030945","url":null,"abstract":"There is a large number of scanned historical documents that need to be indexed for archival and retrieval purposes. A visual word spotting scheme that would serve these purposes is a challenging task even when the transcription of the document image is available. We propose a framework for mapping each word in the transcript to the associated word image in the document. Coarse word mapping based on document constraints is used for lexicon reduction. Then, word mappings are refined using word recognition results by a dynamic programming algorithm that finds the best match while satisfying the constraints.","PeriodicalId":114017,"journal":{"name":"Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition","volume":"39 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":"134626823","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.2002.1030926
L. Q. Zhang, C. Suen
A segmentation based courtesy amount recognition (CAR) system is presented in this paper. A two-stage segmentation module has been proposed, namely the global segmentation stage and the local segmentation stage. At the global segmentation stage, a courtesy amount is coarsely segmented into sub-images according to the spatial relationships of the connected components. These sub-images are then verified by the recognition module and the rejected sub-images are sequentially split using contour analysis at the local segmentation stage. Two neural network classifiers are combined into a recognition module. The isolated digit classifier divides the input patterns into ten numeral classes (0-9), while the holistic double zeros classifier recognizes the cursive and touching double zeros. Experimental results show that the system reads 66.5% bank checks correctly at 0% misreading rate.
{"title":"Recognition of courtesy amounts on bank checks based on a segmentation approach","authors":"L. Q. Zhang, C. Suen","doi":"10.1109/IWFHR.2002.1030926","DOIUrl":"https://doi.org/10.1109/IWFHR.2002.1030926","url":null,"abstract":"A segmentation based courtesy amount recognition (CAR) system is presented in this paper. A two-stage segmentation module has been proposed, namely the global segmentation stage and the local segmentation stage. At the global segmentation stage, a courtesy amount is coarsely segmented into sub-images according to the spatial relationships of the connected components. These sub-images are then verified by the recognition module and the rejected sub-images are sequentially split using contour analysis at the local segmentation stage. Two neural network classifiers are combined into a recognition module. The isolated digit classifier divides the input patterns into ten numeral classes (0-9), while the holistic double zeros classifier recognizes the cursive and touching double zeros. Experimental results show that the system reads 66.5% bank checks correctly at 0% misreading rate.","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":"114254926","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：