Handwritten Signatures are one of the widely used biometrics for document authentication as well as human authorization. The purpose of this paper is to present an off-line signature verification system involving Hindi signatures. Signature verification is a process by which the questioned signature is examined in detail in order to determine whether it belongs to the claimed person or not. Despite of substantial research in the field of signature verification involving Western signatures, very little attention has been dedicated to non-Western signatures such as Chinese, Japanese, Arabic, Persian etc. In this paper, the performance of an off-line signature verification system involving Hindi signatures, whose style is distinct from Western scripts, has been investigated. The gradient and Zernike moment features were employed and Support Vector Machines (SVMs) were considered for verification. To the best of the authors' knowledge, Hindi signatures have never been used for the task of signature verification and this is the first report of using Hindi signatures in this area. The Hindi signature database employed for experimentation consisted of 840 (35×24) genuine signatures and 1050 (35×30) forgeries. An encouraging accuracy of 7.42% FRR and 4.28% FAR were obtained following experimentation when the gradient features were employed.
{"title":"Hindi Off-Line Signature Verification","authors":"S. Pal, M. Blumenstein, U. Pal","doi":"10.1109/ICFHR.2012.212","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.212","url":null,"abstract":"Handwritten Signatures are one of the widely used biometrics for document authentication as well as human authorization. The purpose of this paper is to present an off-line signature verification system involving Hindi signatures. Signature verification is a process by which the questioned signature is examined in detail in order to determine whether it belongs to the claimed person or not. Despite of substantial research in the field of signature verification involving Western signatures, very little attention has been dedicated to non-Western signatures such as Chinese, Japanese, Arabic, Persian etc. In this paper, the performance of an off-line signature verification system involving Hindi signatures, whose style is distinct from Western scripts, has been investigated. The gradient and Zernike moment features were employed and Support Vector Machines (SVMs) were considered for verification. To the best of the authors' knowledge, Hindi signatures have never been used for the task of signature verification and this is the first report of using Hindi signatures in this area. The Hindi signature database employed for experimentation consisted of 840 (35×24) genuine signatures and 1050 (35×30) forgeries. An encouraging accuracy of 7.42% FRR and 4.28% FAR were obtained following experimentation when the gradient features were employed.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"158 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130079612","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}
For highly degraded text documents, common tasks such as binarization and line extraction, remain difficult tasks. Equipped with a reliable information regarding the distribution of character dimensions in the document, one can improve results of these algorithms significantly. We introduce a novel perspective of the image data which maps the evolution of connected components along the change in gray scale threshold. We use these maps to provide a robust algorithm for extracting information about character dimensions in degraded documents, and demonstrate improvement in binarization results using this information. We analyze statistically the characteristics of the evolution maps for text documents, and compare our results with ground truth data.
{"title":"Evolution Maps for Connected Components in Text Documents","authors":"Ofer Biller, K. Kedem, I. Dinstein, Jihad El-Sana","doi":"10.1109/ICFHR.2012.201","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.201","url":null,"abstract":"For highly degraded text documents, common tasks such as binarization and line extraction, remain difficult tasks. Equipped with a reliable information regarding the distribution of character dimensions in the document, one can improve results of these algorithms significantly. We introduce a novel perspective of the image data which maps the evolution of connected components along the change in gray scale threshold. We use these maps to provide a robust algorithm for extracting information about character dimensions in degraded documents, and demonstrate improvement in binarization results using this information. We analyze statistically the characteristics of the evolution maps for text documents, and compare our results with ground truth data.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"152 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133923344","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}
Volkmar Frinken, Markus Baumgartner, Andreas Fischer, H. Bunke
State-of-the-art handwriting recognition systems are learning-based systems that require large sets of training data. The creation of training data, and consequently the creation of a well-performing recognition system, requires therefore a substantial amount of human work. This can be reduced with semi-supervised learning, which uses unlabeled text lines for training as well. Current approaches estimate the correct transcription of the unlabeled data via handwriting recognition which is not only extremely demanding as far as computational costs are concerned but also requires a good model of the target language. In this paper, we propose a different approach that makes use of keyword spotting, which is significantly faster and does not need any language model. In a set of experiments we demonstrate its superiority over existing approaches.
{"title":"Semi-supervised learning for cursive handwriting recognition using keyword spotting","authors":"Volkmar Frinken, Markus Baumgartner, Andreas Fischer, H. Bunke","doi":"10.1109/ICFHR.2012.268","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.268","url":null,"abstract":"State-of-the-art handwriting recognition systems are learning-based systems that require large sets of training data. The creation of training data, and consequently the creation of a well-performing recognition system, requires therefore a substantial amount of human work. This can be reduced with semi-supervised learning, which uses unlabeled text lines for training as well. Current approaches estimate the correct transcription of the unlabeled data via handwriting recognition which is not only extremely demanding as far as computational costs are concerned but also requires a good model of the target language. In this paper, we propose a different approach that makes use of keyword spotting, which is significantly faster and does not need any language model. In a set of experiments we demonstrate its superiority over existing approaches.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128260926","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}
Fotini Simistira, V. Papavassiliou, V. Katsouros, G. Carayannis
We present a system for recognizing online mathematical expressions (ME). Symbol recognition is based on a template elastic matching distance between pen direction features. The structural analysis of the ME is based on extracting the baseline of the ME and then classifying symbols into levels above and below the baseline. The symbols are then sequentially analyzed using six spatial relations and a respective 2d structure is processed to give the resulting MathML representation of the ME. The system was evaluated on the Competition on Recognition of Online Handwritten Mathematical Expressions (CROHME) 2011 datasets and demonstrates promising results.
{"title":"A System for Recognition of On-Line Handwritten Mathematical Expressions","authors":"Fotini Simistira, V. Papavassiliou, V. Katsouros, G. Carayannis","doi":"10.1109/ICFHR.2012.172","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.172","url":null,"abstract":"We present a system for recognizing online mathematical expressions (ME). Symbol recognition is based on a template elastic matching distance between pen direction features. The structural analysis of the ME is based on extracting the baseline of the ME and then classifying symbols into levels above and below the baseline. The symbols are then sequentially analyzed using six spatial relations and a respective 2d structure is processed to give the resulting MathML representation of the ME. The system was evaluated on the Competition on Recognition of Online Handwritten Mathematical Expressions (CROHME) 2011 datasets and demonstrates promising results.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126906290","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}
U. Porwal, Chetan Ramaiah, Arti Shivram, V. Govindaraju
Availability of sufficient labeled data is key to the performance of any learning algorithm. However, in document analysis obtaining the large amount of labeled data is difficult. Scarcity of labeled samples is often a main bottleneck in the performance of algorithms for document analysis. However, unlabeled data samples are present in abundance. We propose a semi supervised framework for writer identification for offline handwritten documents that leverages the information hidden in the unlabeled samples. The task of writer identification is a complex one and our framework tries to model the nuances of handwriting with the use of structural learning. This framework models the complexity of learning problem by selecting the best hypotheses space by breaking the main task into several sub tasks. All the hypotheses spaces pertaining to the sub tasks will be used for the best model selection by retrieving a common optimal sub structure that has high correspondence with all of the candidate hypotheses spaces. We have used publically available IAM data set to show the efficacy of our method.
{"title":"Structural Learning for Writer Identification in Offline Handwriting","authors":"U. Porwal, Chetan Ramaiah, Arti Shivram, V. Govindaraju","doi":"10.1109/ICFHR.2012.277","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.277","url":null,"abstract":"Availability of sufficient labeled data is key to the performance of any learning algorithm. However, in document analysis obtaining the large amount of labeled data is difficult. Scarcity of labeled samples is often a main bottleneck in the performance of algorithms for document analysis. However, unlabeled data samples are present in abundance. We propose a semi supervised framework for writer identification for offline handwritten documents that leverages the information hidden in the unlabeled samples. The task of writer identification is a complex one and our framework tries to model the nuances of handwriting with the use of structural learning. This framework models the complexity of learning problem by selecting the best hypotheses space by breaking the main task into several sub tasks. All the hypotheses spaces pertaining to the sub tasks will be used for the best model selection by retrieving a common optimal sub structure that has high correspondence with all of the candidate hypotheses spaces. We have used publically available IAM data set to show the efficacy of our method.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114145102","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}
A new approach for verifying off-line Persian signatures is presented, in this paper. In our method, feature extraction step is conducted based on estimated Fractal Dimension (FD) of signatures images, and making decision about acceptance/rejection of test signature is formulated as testing hypothesis which is used for the first time in order to verify offline Persian signatures. The proposed method has been tested on our new created database included 1000 genuine signatures and 200 skilled forgeries which have been collected from a population of 100 human subjects with different educational background. Obtained results confirm the effectiveness of the presented method.
{"title":"Persian Signature Verification Based on Fractal Dimension Using Testing Hypothesis","authors":"A. Foroozandeh, Y. Akbari, M. Jalili, J. Sadri","doi":"10.1109/ICFHR.2012.254","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.254","url":null,"abstract":"A new approach for verifying off-line Persian signatures is presented, in this paper. In our method, feature extraction step is conducted based on estimated Fractal Dimension (FD) of signatures images, and making decision about acceptance/rejection of test signature is formulated as testing hypothesis which is used for the first time in order to verify offline Persian signatures. The proposed method has been tested on our new created database included 1000 genuine signatures and 200 skilled forgeries which have been collected from a population of 100 human subjects with different educational background. Obtained results confirm the effectiveness of the presented method.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116730193","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}
In this paper we present the importance of including the user in the loop in a handwritten word spotting framework. Several off-the-shelf query fusion and relevance feedback strategies have been tested in the handwritten word spotting context. The increase in terms of precision when the user is included in the loop is assessed using two datasets of historical handwritten documents and a baseline word spotting approach based on a bag-of-visual-words model.
{"title":"The role of the users in handwritten word spotting applications: query fusion and relevance feedback","authors":"Marçal Rusiñol, J. Lladós","doi":"10.1109/ICFHR.2012.282","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.282","url":null,"abstract":"In this paper we present the importance of including the user in the loop in a handwritten word spotting framework. Several off-the-shelf query fusion and relevance feedback strategies have been tested in the handwritten word spotting context. The increase in terms of precision when the user is included in the loop is assessed using two datasets of historical handwritten documents and a baseline word spotting approach based on a bag-of-visual-words model.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124989656","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}
Tabular structure detection and recognition can be a valuable step in the analysis of unstructured documents. The noisy handwritten documents we try to analyze may contain pre-printed rulings as the substrate, hand-drawn rulings, machine-printed text, handwritten text, and signatures, in addition to the tabular structures which we wish to decompose into basic cells, rows, and columns. Although work has been done to machine-printed documents, noisy handwritten documents may require modified and/or new techniques. In this work, we try to detect and decompose tabular structures into 2-D grids of table cells simultaneously. First, we detect "key points" that help determine the physical and logical structure of tables. Then, we make use of the 2-D grid assumption to build grids of key points. Finally, we extract structural features for the Min-Cut/Max-Flow algorithm to recognize tabular structures. Experiments on 22 tables which contain 584 table cells show a cell precision of 100% and a cell recall of 93.3%.
{"title":"Model-Based Tabular Structure Detection and Recognition in Noisy Handwritten Documents","authors":"Jin Chen, D. Lopresti","doi":"10.1109/ICFHR.2012.233","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.233","url":null,"abstract":"Tabular structure detection and recognition can be a valuable step in the analysis of unstructured documents. The noisy handwritten documents we try to analyze may contain pre-printed rulings as the substrate, hand-drawn rulings, machine-printed text, handwritten text, and signatures, in addition to the tabular structures which we wish to decompose into basic cells, rows, and columns. Although work has been done to machine-printed documents, noisy handwritten documents may require modified and/or new techniques. In this work, we try to detect and decompose tabular structures into 2-D grids of table cells simultaneously. First, we detect \"key points\" that help determine the physical and logical structure of tables. Then, we make use of the 2-D grid assumption to build grids of key points. Finally, we extract structural features for the Min-Cut/Max-Flow algorithm to recognize tabular structures. Experiments on 22 tables which contain 584 table cells show a cell precision of 100% and a cell recall of 93.3%.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125248661","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}
S. Uchida, R. Ishida, A. Yoshida, Wenjie Cai, Yaokai Feng
The ambitious goal of this research is to understand the real distribution of character patterns. Ideally, if we can collect all possible character patterns, we can totally understand how they are distributed in the image space. In addition, we also have the perfect character recognizer because we know the correct class for any character image. Of course, it is practically impossible to collect all those patterns - however, if we collect character patterns massively and analyze how the distribution changes according to the increase of patterns, we will be able to estimate the real distribution asymptotically. For this purpose, we use 822,714 manually ground-truthed 32×32 handwritten digit patterns in this paper. The distribution of those patterns are observed by nearest neighbor analysis and network analysis, both of which do not make any approximation (such as low-dimensional representation) and thus do not corrupt the details of the distribution.
{"title":"Character Image Patterns as Big Data","authors":"S. Uchida, R. Ishida, A. Yoshida, Wenjie Cai, Yaokai Feng","doi":"10.1109/ICFHR.2012.190","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.190","url":null,"abstract":"The ambitious goal of this research is to understand the real distribution of character patterns. Ideally, if we can collect all possible character patterns, we can totally understand how they are distributed in the image space. In addition, we also have the perfect character recognizer because we know the correct class for any character image. Of course, it is practically impossible to collect all those patterns - however, if we collect character patterns massively and analyze how the distribution changes according to the increase of patterns, we will be able to estimate the real distribution asymptotically. For this purpose, we use 822,714 manually ground-truthed 32×32 handwritten digit patterns in this paper. The distribution of those patterns are observed by nearest neighbor analysis and network analysis, both of which do not make any approximation (such as low-dimensional representation) and thus do not corrupt the details of the distribution.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122892159","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}
Three different strategies in order to re-train classifiers, when new labeled data become available, are presented in a multi-expert scenario. The first method is the use of the entire new dataset. The second one is related to the consideration that each single classifier is able to select new samples starting from those on which it performs a missclassification. Finally, by inspecting the multi expert system behavior, a sample misclassified by an expert, is used to update that classifier only if it produces a miss-classification by the ensemble of classifiers. This paper provides a comparison of three approaches under different conditions on two state of the art classifiers (SVM and Naive Bayes) by taking into account four different combination techniques. Experiments have been performed by considering the CEDAR (handwritten digit) database. It is shown how results depend by the amount of the new training samples, as well as by the specific combination decision schema and by classifiers in the ensemble.
{"title":"Benchmarking of update learning strategies on digit classifier systems","authors":"D. Barbuzzi, D. Impedovo, G. Pirlo","doi":"10.1109/ICFHR.2012.186","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.186","url":null,"abstract":"Three different strategies in order to re-train classifiers, when new labeled data become available, are presented in a multi-expert scenario. The first method is the use of the entire new dataset. The second one is related to the consideration that each single classifier is able to select new samples starting from those on which it performs a missclassification. Finally, by inspecting the multi expert system behavior, a sample misclassified by an expert, is used to update that classifier only if it produces a miss-classification by the ensemble of classifiers. This paper provides a comparison of three approaches under different conditions on two state of the art classifiers (SVM and Naive Bayes) by taking into account four different combination techniques. Experiments have been performed by considering the CEDAR (handwritten digit) database. It is shown how results depend by the amount of the new training samples, as well as by the specific combination decision schema and by classifiers in the ensemble.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128090403","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：