Pub Date : 2001-09-10DOI: 10.1109/ICDAR.2001.953879
Hiroshi Shinjo, Eiichi Hadano, K. Marukawa, Y. Shima, H. Sako
It is very difficult to analyze form structures because of breaks in lines and additional noises in the form image. This paper focuses on cell recognition in low quality form images. The recognition method has two features to achieve robustness in cell recognition. One is grid representation using several types of intersection and the terminal points of the frame lines. The other is the recursive modification of the representation. A new representation is created according to the determination of the breaks in the line and the hypothesized location of the missed intersections by using the previous representation. The modification is processed recursively until the representation has perfect consistency and all form cells are detected. In an experiment using 1565 form samples, all cells in 1538 samples (98.3% of 1565 samples) were recognized correctly by this method.
{"title":"A recursive analysis for form cell recognition","authors":"Hiroshi Shinjo, Eiichi Hadano, K. Marukawa, Y. Shima, H. Sako","doi":"10.1109/ICDAR.2001.953879","DOIUrl":"https://doi.org/10.1109/ICDAR.2001.953879","url":null,"abstract":"It is very difficult to analyze form structures because of breaks in lines and additional noises in the form image. This paper focuses on cell recognition in low quality form images. The recognition method has two features to achieve robustness in cell recognition. One is grid representation using several types of intersection and the terminal points of the frame lines. The other is the recursive modification of the representation. A new representation is created according to the determination of the breaks in the line and the hypothesized location of the missed intersections by using the previous representation. The modification is processed recursively until the representation has perfect consistency and all form cells are detected. In an experiment using 1565 form samples, all cells in 1538 samples (98.3% of 1565 samples) were recognized correctly by this method.","PeriodicalId":277816,"journal":{"name":"Proceedings of Sixth International Conference on Document Analysis and Recognition","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133819625","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 : 2001-09-10DOI: 10.1109/ICDAR.2001.953886
S. Marukatat, T. Artières, P. Gallinari, B. Dorizzi
This paper focuses on designing a handwriting recognition system dealing with on-line signal, i.e. temporal handwriting signal captured through an electronic pen or a digitalized tablet. We present here some new results concerning a hybrid on-line handwriting recognition system based on Hidden Markov Models (HMMs) and Neural Networks (NNs), which has already been presented in several contributions. In our approach, a letter-model is a Left-Right HMM, whose emission probability densities are approximated with mixtures of predictive multilayer perceptrons. The basic letter models are cascaded in order to build models for words and sentences. At the word level, recognition is performed thanks to a dictionary organized with a tree-structure. At the sentence level, a word-predecessor conditioned frame synchronous beam search algorithm allows to perform simultaneously segmentation into words and word recognition. It processes through the building of a word graph from which a set of candidate sentences may be extracted. Word and sentence recognition performances are evaluated on parts of the UNIPEN international database.
{"title":"Sentence recognition through hybrid neuro-Markovian modeling","authors":"S. Marukatat, T. Artières, P. Gallinari, B. Dorizzi","doi":"10.1109/ICDAR.2001.953886","DOIUrl":"https://doi.org/10.1109/ICDAR.2001.953886","url":null,"abstract":"This paper focuses on designing a handwriting recognition system dealing with on-line signal, i.e. temporal handwriting signal captured through an electronic pen or a digitalized tablet. We present here some new results concerning a hybrid on-line handwriting recognition system based on Hidden Markov Models (HMMs) and Neural Networks (NNs), which has already been presented in several contributions. In our approach, a letter-model is a Left-Right HMM, whose emission probability densities are approximated with mixtures of predictive multilayer perceptrons. The basic letter models are cascaded in order to build models for words and sentences. At the word level, recognition is performed thanks to a dictionary organized with a tree-structure. At the sentence level, a word-predecessor conditioned frame synchronous beam search algorithm allows to perform simultaneously segmentation into words and word recognition. It processes through the building of a word graph from which a set of candidate sentences may be extracted. Word and sentence recognition performances are evaluated on parts of the UNIPEN international database.","PeriodicalId":277816,"journal":{"name":"Proceedings of Sixth International Conference on Document Analysis and Recognition","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124365946","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 : 2001-09-10DOI: 10.1109/ICDAR.2001.953842
B. Klein, Serdar Gökkus, T. Kieninger, A. Dengel
This paper introduces three approaches for an industrial, comprehensive document analysis system to enable it to spot tables in documents. Searching for a set of known table headers (approach 1) works rather well in a significant number of documents. But this approach (though it is implemented tolerant to OCR errors) is not tolerant enough towards some kinds of even minor aberrations. This not only decreases the recognition results, but also, even worse, makes users feel uncomfortable. Pragmatically trying to mimic for what the human eyes might key, leads to our two further, complementary approaches: searching for layout structures which resemble parts of columns (approach 2), and searching for groupings of similar lines (approach 3). The suitability of the approaches for our system requires them to be very simple to implement and simple to explain to users, computationally cheap, and combinable. In the domain of health insurances who receive huge amounts of so called medical liquidations on a daily basis we obtain very good results. On document samples representative for the every day practice of five customers-health insurance companies-tables were spotted as good and as fast as the customers expected the system to be. We thus consider our current approaches as a step towards cognitive adequacy.
{"title":"Three approaches to \"industrial\" table spotting","authors":"B. Klein, Serdar Gökkus, T. Kieninger, A. Dengel","doi":"10.1109/ICDAR.2001.953842","DOIUrl":"https://doi.org/10.1109/ICDAR.2001.953842","url":null,"abstract":"This paper introduces three approaches for an industrial, comprehensive document analysis system to enable it to spot tables in documents. Searching for a set of known table headers (approach 1) works rather well in a significant number of documents. But this approach (though it is implemented tolerant to OCR errors) is not tolerant enough towards some kinds of even minor aberrations. This not only decreases the recognition results, but also, even worse, makes users feel uncomfortable. Pragmatically trying to mimic for what the human eyes might key, leads to our two further, complementary approaches: searching for layout structures which resemble parts of columns (approach 2), and searching for groupings of similar lines (approach 3). The suitability of the approaches for our system requires them to be very simple to implement and simple to explain to users, computationally cheap, and combinable. In the domain of health insurances who receive huge amounts of so called medical liquidations on a daily basis we obtain very good results. On document samples representative for the every day practice of five customers-health insurance companies-tables were spotted as good and as fast as the customers expected the system to be. We thus consider our current approaches as a step towards cognitive adequacy.","PeriodicalId":277816,"journal":{"name":"Proceedings of Sixth International Conference on Document Analysis and Recognition","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115997651","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 : 2001-09-10DOI: 10.1109/ICDAR.2001.953936
K. Sirlantzis, M. Fairhurst
In this paper we introduce a global optimisation technique, namely a genetic algorithm, into a parallel multiclassifier system design process. As few similar systems have been proposed to date our main focus in this study is to explore the statistical properties of the self-configuration process in order to enhance our understanding of its internal operational mechanism and to propose possible improvements. For this we tested our system in a series of character recognition tasks ranging from printed to handwritten data. Subsequently, we compare its performance with that of two alternative multiple classifier combination strategies. Finally, we investigate, over a set of cross-validating experiments, the relation between the performances of the individual classifiers and their variability, and the frequency with which each of them is chosen to participate in the final configuration generated by the genetic algorithm.
{"title":"Investigation of a novel self-configurable multiple classifier system for character recognition","authors":"K. Sirlantzis, M. Fairhurst","doi":"10.1109/ICDAR.2001.953936","DOIUrl":"https://doi.org/10.1109/ICDAR.2001.953936","url":null,"abstract":"In this paper we introduce a global optimisation technique, namely a genetic algorithm, into a parallel multiclassifier system design process. As few similar systems have been proposed to date our main focus in this study is to explore the statistical properties of the self-configuration process in order to enhance our understanding of its internal operational mechanism and to propose possible improvements. For this we tested our system in a series of character recognition tasks ranging from printed to handwritten data. Subsequently, we compare its performance with that of two alternative multiple classifier combination strategies. Finally, we investigate, over a set of cross-validating experiments, the relation between the performances of the individual classifiers and their variability, and the frequency with which each of them is chosen to participate in the final configuration generated by the genetic algorithm.","PeriodicalId":277816,"journal":{"name":"Proceedings of Sixth International Conference on Document Analysis and Recognition","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123476905","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 : 2001-09-10DOI: 10.1109/ICDAR.2001.953837
A. Brakensiek, A. Kosmala, G. Rigoll
This paper describes an online handwriting recognition system with focus on adaptation techniques. Our hidden Markov model (HMM)-based recognition system for cursive German script can be adapted to the writing style of a new writer using either a retraining depending on the EM (expectation maximization)-approach or an adaptation according to the MAP (maximum a posteriori) or MLLR (maximum likelihood linear regression)-criterion. The performance of the resulting writer-dependent system increases significantly even if the amount of adaptation data is very small (about 6 words). So this approach is also applicable for online systems in hand-held computers such as PDAs. Special attention was paid to the performance comparison of the different adaptation techniques with the availability of different amounts of adaptation data ranging from a few words tip to 100 words per writer.
{"title":"Comparing adaptation techniques for on-line handwriting recognition","authors":"A. Brakensiek, A. Kosmala, G. Rigoll","doi":"10.1109/ICDAR.2001.953837","DOIUrl":"https://doi.org/10.1109/ICDAR.2001.953837","url":null,"abstract":"This paper describes an online handwriting recognition system with focus on adaptation techniques. Our hidden Markov model (HMM)-based recognition system for cursive German script can be adapted to the writing style of a new writer using either a retraining depending on the EM (expectation maximization)-approach or an adaptation according to the MAP (maximum a posteriori) or MLLR (maximum likelihood linear regression)-criterion. The performance of the resulting writer-dependent system increases significantly even if the amount of adaptation data is very small (about 6 words). So this approach is also applicable for online systems in hand-held computers such as PDAs. Special attention was paid to the performance comparison of the different adaptation techniques with the availability of different amounts of adaptation data ranging from a few words tip to 100 words per writer.","PeriodicalId":277816,"journal":{"name":"Proceedings of Sixth International Conference on Document Analysis and Recognition","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126140556","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 : 2001-09-10DOI: 10.1109/ICDAR.2001.953942
E. Justino, Flávio Bortolozzi, R. Sabourin
The problem of signature verification is in theory a pattern recognition task used to discriminate two classes, original and forgery signatures. Even after many efforts in order to develop new verification techniques for static signature verification, the influence of the forgery types has not been extensively studied. This paper reports the contribution to signature verification considering different forgery types in an HMM framework. The experiments have shown that the error rates of the simple and random forgery signatures are very closed. This reflects the real applications in which the simple forgeries represent the principal fraudulent case. In addition, the experiments show promising results in skilled forgery verification by using simple static and pseudodynamic features.
{"title":"Off-line signature verification using HMM for random, simple and skilled forgeries","authors":"E. Justino, Flávio Bortolozzi, R. Sabourin","doi":"10.1109/ICDAR.2001.953942","DOIUrl":"https://doi.org/10.1109/ICDAR.2001.953942","url":null,"abstract":"The problem of signature verification is in theory a pattern recognition task used to discriminate two classes, original and forgery signatures. Even after many efforts in order to develop new verification techniques for static signature verification, the influence of the forgery types has not been extensively studied. This paper reports the contribution to signature verification considering different forgery types in an HMM framework. The experiments have shown that the error rates of the simple and random forgery signatures are very closed. This reflects the real applications in which the simple forgeries represent the principal fraudulent case. In addition, the experiments show promising results in skilled forgery verification by using simple static and pseudodynamic features.","PeriodicalId":277816,"journal":{"name":"Proceedings of Sixth International Conference on Document Analysis and Recognition","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124972658","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 : 2001-09-10DOI: 10.1109/ICDAR.2001.953819
Luiz Oliveira, R. Sabourin, Flávio Bortolozzi, C. Suen
The paper presents a modular system to recognize numerical amounts on Brazilian bank cheques. The system uses a segmentation-based recognition approach and the recognition function is based on a recognition and verification strategy. Our approach consists of combining the outputs from different levels such as segmentation, recognition and post-processing in a probabilistic model. A new feature set is introduced to the verifier module in order to detect segmentation effects such as over-segmentation and under-segmentation. Finally, we present experimental results on two databases: numerical amounts and NIST SD19. The latter aims at validating the concept of modular system and showing the robustness of the system over a well-known database.
{"title":"A modular system to recognize numerical amounts on Brazilian bank cheques","authors":"Luiz Oliveira, R. Sabourin, Flávio Bortolozzi, C. Suen","doi":"10.1109/ICDAR.2001.953819","DOIUrl":"https://doi.org/10.1109/ICDAR.2001.953819","url":null,"abstract":"The paper presents a modular system to recognize numerical amounts on Brazilian bank cheques. The system uses a segmentation-based recognition approach and the recognition function is based on a recognition and verification strategy. Our approach consists of combining the outputs from different levels such as segmentation, recognition and post-processing in a probabilistic model. A new feature set is introduced to the verifier module in order to detect segmentation effects such as over-segmentation and under-segmentation. Finally, we present experimental results on two databases: numerical amounts and NIST SD19. The latter aims at validating the concept of modular system and showing the robustness of the system over a well-known database.","PeriodicalId":277816,"journal":{"name":"Proceedings of Sixth International Conference on Document Analysis and Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128738673","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 : 2001-09-10DOI: 10.1109/ICDAR.2001.953750
Liying Fan, Lixin Fan, C. Tan
We propose a novel coplanar filter, which exploits the coplanarity of gray-level distribution of neighboring pixels, to pre-filter the document images. Experiments show that the proposed filter exhibits the following desired properties for document image binarization: 1) impulsive noise removal, 2) piecewise smoothing, and 3) sharp edge preservation.
{"title":"Binarizing document image using coplanar prefilter","authors":"Liying Fan, Lixin Fan, C. Tan","doi":"10.1109/ICDAR.2001.953750","DOIUrl":"https://doi.org/10.1109/ICDAR.2001.953750","url":null,"abstract":"We propose a novel coplanar filter, which exploits the coplanarity of gray-level distribution of neighboring pixels, to pre-filter the document images. Experiments show that the proposed filter exhibits the following desired properties for document image binarization: 1) impulsive noise removal, 2) piecewise smoothing, and 3) sharp edge preservation.","PeriodicalId":277816,"journal":{"name":"Proceedings of Sixth International Conference on Document Analysis and Recognition","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130007214","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 : 2001-09-10DOI: 10.1109/ICDAR.2001.953831
Ernest Valveny, E. Martí
Accurate symbol recognition in graphic documents needs an accurate representation of the symbols to be recognized. If structural approaches are used for recognition, symbols have to be described in terms of their shape, using structural relationships among extracted features. Unlike statistical pattern recognition, in structural methods, symbols are usually, manually defined from expertise knowledge, and not automatically, inferred from sample images. In this work we explain one approach to learn from examples a representative structural description of a symbol, thus providing better information about shape variability. The description of a symbol is based on a probabilistic model. It consists of a set of lines described by, the mean and the variance of line parameters, respectively, providing information about the model of the symbol, and its shape variability. The representation of each image in the sample set as a set of lines is achieved using deformable template matching.
{"title":"Learning of structural descriptions of graphic symbols using deformable template matching","authors":"Ernest Valveny, E. Martí","doi":"10.1109/ICDAR.2001.953831","DOIUrl":"https://doi.org/10.1109/ICDAR.2001.953831","url":null,"abstract":"Accurate symbol recognition in graphic documents needs an accurate representation of the symbols to be recognized. If structural approaches are used for recognition, symbols have to be described in terms of their shape, using structural relationships among extracted features. Unlike statistical pattern recognition, in structural methods, symbols are usually, manually defined from expertise knowledge, and not automatically, inferred from sample images. In this work we explain one approach to learn from examples a representative structural description of a symbol, thus providing better information about shape variability. The description of a symbol is based on a probabilistic model. It consists of a set of lines described by, the mean and the variance of line parameters, respectively, providing information about the model of the symbol, and its shape variability. The representation of each image in the sample set as a set of lines is achieved using deformable template matching.","PeriodicalId":277816,"journal":{"name":"Proceedings of Sixth International Conference on Document Analysis and Recognition","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130675678","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 : 2001-09-10DOI: 10.1109/ICDAR.2001.953948
Kenichi Toyozumi, K. Mori, Y. Suenaga, Takahiro Suzuki
This paper presents an expanded system for the online recognition of handwritten mathematical formulas. Our target handwritten mathematical formulas are strokes drawn on a data tablet. This system recognizes such strokes as components of mathematical formulas on the basis of their positions and combinations. Including matrix structures, general mathematical expressions are acceptable for this system. Each recognition result is acquired as a L/sup A/T/sub E/X source code. This system also has a preview function to enable a more highly intuitive recognition result. In recognition experiments, this system proved to be fairly feasible in handling handwritten mathematical formulas in real-time.
本文提出了一个用于手写数学公式在线识别的扩展系统。我们的目标是手写的数学公式是在数据板上画的。该系统根据笔画的位置和组合将笔画识别为数学公式的组成部分。包括矩阵结构，一般的数学表达式是可以接受的系统。每个识别结果作为L/sup a /T/sub E/X源代码获得。该系统还具有预览功能，使识别结果更加直观。在识别实验中，该系统对手写数学公式的实时处理是相当可行的。
{"title":"A system for real-time recognition of handwritten mathematical formulas","authors":"Kenichi Toyozumi, K. Mori, Y. Suenaga, Takahiro Suzuki","doi":"10.1109/ICDAR.2001.953948","DOIUrl":"https://doi.org/10.1109/ICDAR.2001.953948","url":null,"abstract":"This paper presents an expanded system for the online recognition of handwritten mathematical formulas. Our target handwritten mathematical formulas are strokes drawn on a data tablet. This system recognizes such strokes as components of mathematical formulas on the basis of their positions and combinations. Including matrix structures, general mathematical expressions are acceptable for this system. Each recognition result is acquired as a L/sup A/T/sub E/X source code. This system also has a preview function to enable a more highly intuitive recognition result. In recognition experiments, this system proved to be fairly feasible in handling handwritten mathematical formulas in real-time.","PeriodicalId":277816,"journal":{"name":"Proceedings of Sixth International Conference on Document Analysis and Recognition","volume":"2017 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132884008","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：