Prasanth, Jagadeesh Babu, Raghunath Sharma, Prabhakara Rao, Dinesh Mandalapu, L. Prasanth, V. Jagadeesh Babu, R. Raghunath, Sharma Dinesh, M. G. V. P. Rao
This paper describes character based elastic matching using local features for recognizing online handwritten data. Dynamic time warping (DTW) has been used with four different feature sets: x-y features, shape context (SC) and tangent angle (TA) features, generalized shape context feature (GSC) and the fourth set containing x-y, normalized first and second derivatives and curvature features. Nearest neighborhood classifier with DTW distance was used as the classifier. In comparison, the SC and TA feature set was found to be the slowest and the fourth set was best among all in the recognition rate. The results have been compiled for the online handwritten Tamil and Telugu data. On Telugu data we obtained an accuracy of 90.6% with a speed of 0.166 symbols/sec. To increase the speed we have proposed a 2-stage recognition scheme using which we obtained accuracy of 89.77% but with a speed of 3.977 symbols/sec.
{"title":"Elastic Matching of Online Handwritten Tamil and Telugu Scripts Using Local Features","authors":"Prasanth, Jagadeesh Babu, Raghunath Sharma, Prabhakara Rao, Dinesh Mandalapu, L. Prasanth, V. Jagadeesh Babu, R. Raghunath, Sharma Dinesh, M. G. V. P. Rao","doi":"10.1109/ICDAR.2007.106","DOIUrl":"https://doi.org/10.1109/ICDAR.2007.106","url":null,"abstract":"This paper describes character based elastic matching using local features for recognizing online handwritten data. Dynamic time warping (DTW) has been used with four different feature sets: x-y features, shape context (SC) and tangent angle (TA) features, generalized shape context feature (GSC) and the fourth set containing x-y, normalized first and second derivatives and curvature features. Nearest neighborhood classifier with DTW distance was used as the classifier. In comparison, the SC and TA feature set was found to be the slowest and the fourth set was best among all in the recognition rate. The results have been compiled for the online handwritten Tamil and Telugu data. On Telugu data we obtained an accuracy of 90.6% with a speed of 0.166 symbols/sec. To increase the speed we have proposed a 2-stage recognition scheme using which we obtained accuracy of 89.77% but with a speed of 3.977 symbols/sec.","PeriodicalId":279268,"journal":{"name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129983384","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 : 2007-09-23DOI: 10.1109/ICDAR.2007.4377032
J. Vargas-Bonilla, M. A. Ferrer-Ballester, C. Travieso-González, J. B. Alonso
The effect of changing the image resolution over an off-line signature verification system performance is analyzed. The geometrical features used for the system analyzed in this paper are based on two vectors which represent the envelope and the interior stroke distribution in polar and Cartesian coordinates. Image resolution is progressively diminished from an initial 600 ppp resolution till 45 ppp. The robustness of the analyzed system for random and simple forgeries is tested out with a hidden Markov model. The results show that 150 ppp offers a good trade-off between performance and image resolution for static features.
{"title":"Off-line Signature Verification System Performance against Image Acquisition Resolution","authors":"J. Vargas-Bonilla, M. A. Ferrer-Ballester, C. Travieso-González, J. B. Alonso","doi":"10.1109/ICDAR.2007.4377032","DOIUrl":"https://doi.org/10.1109/ICDAR.2007.4377032","url":null,"abstract":"The effect of changing the image resolution over an off-line signature verification system performance is analyzed. The geometrical features used for the system analyzed in this paper are based on two vectors which represent the envelope and the interior stroke distribution in polar and Cartesian coordinates. Image resolution is progressively diminished from an initial 600 ppp resolution till 45 ppp. The robustness of the analyzed system for random and simple forgeries is tested out with a hidden Markov model. The results show that 150 ppp offers a good trade-off between performance and image resolution for static features.","PeriodicalId":279268,"journal":{"name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131096448","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. Toselli, Verónica Romero, Luis Rodríguez, E. Vidal
To date, automatic handwriting recognition systems are far from being perfect and often they need a post editing where a human intervention is required to check and correct the results of such systems. We propose to have a new interactive, on-line framework which, rather than full automation, aims at assisting the human in the proper recognition- transcription process; that is, facilitate and speed up their transcription task of handwritten texts. This framework combines the efficiency of automatic handwriting recognition systems with the accuracy of the human transcriptor. The best result is a cost-effective perfect transcription of the handwriting text images.
{"title":"Computer Assisted Transcription of Handwritten Text Images","authors":"A. Toselli, Verónica Romero, Luis Rodríguez, E. Vidal","doi":"10.1109/ICDAR.2007.86","DOIUrl":"https://doi.org/10.1109/ICDAR.2007.86","url":null,"abstract":"To date, automatic handwriting recognition systems are far from being perfect and often they need a post editing where a human intervention is required to check and correct the results of such systems. We propose to have a new interactive, on-line framework which, rather than full automation, aims at assisting the human in the proper recognition- transcription process; that is, facilitate and speed up their transcription task of handwritten texts. This framework combines the efficiency of automatic handwriting recognition systems with the accuracy of the human transcriptor. The best result is a cost-effective perfect transcription of the handwriting text images.","PeriodicalId":279268,"journal":{"name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116024356","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}
The main contribution of the paper is that it presents a suffix tree based data structure for automatic handwritten Chinese address reading. Since lots of papers have discussed the destination address block (DAB) location for Chinese, we will not extend it in this paper. Instead, we pay more attention to improve the address matching performance after DAB location. As some conventional methods, the extracted text lines are pre-segmented into a series of radicals. We then build a hierarchical structure of sub-strings from the recognized characters of valid radical combinations. Coarse address candidates are selected at the same time. In address maching, we incorporate postcode information to filter redundant addresses. The pre- segmented radicals are compared with candidate address and a cost function combining recognition and structrual cost is evaluated for final decision. In the system, character segmentation, recognition, string searching and matching are considered synchronously by taking advantage of lexicon knowledge. Suffix tree can greatly facilitate the substring generation process and enable the matching process to start from any character to collect potentially bitty information. Therefore, our algorithms is more robust to the intervening noises and irregular writing styles. Finallly, we test 1,000 handwritten Chinese envelopes and achieve a correct rate of 85.30% in 3.0 seconds per mail averagely.
{"title":"A Suffix Tree Based Handwritten Chinese Address Recognition System","authors":"Y. Jiang, X. Ding, Z. Ren","doi":"10.1109/ICDAR.2007.36","DOIUrl":"https://doi.org/10.1109/ICDAR.2007.36","url":null,"abstract":"The main contribution of the paper is that it presents a suffix tree based data structure for automatic handwritten Chinese address reading. Since lots of papers have discussed the destination address block (DAB) location for Chinese, we will not extend it in this paper. Instead, we pay more attention to improve the address matching performance after DAB location. As some conventional methods, the extracted text lines are pre-segmented into a series of radicals. We then build a hierarchical structure of sub-strings from the recognized characters of valid radical combinations. Coarse address candidates are selected at the same time. In address maching, we incorporate postcode information to filter redundant addresses. The pre- segmented radicals are compared with candidate address and a cost function combining recognition and structrual cost is evaluated for final decision. In the system, character segmentation, recognition, string searching and matching are considered synchronously by taking advantage of lexicon knowledge. Suffix tree can greatly facilitate the substring generation process and enable the matching process to start from any character to collect potentially bitty information. Therefore, our algorithms is more robust to the intervening noises and irregular writing styles. Finallly, we test 1,000 handwritten Chinese envelopes and achieve a correct rate of 85.30% in 3.0 seconds per mail averagely.","PeriodicalId":279268,"journal":{"name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122396803","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 : 2007-09-23DOI: 10.1109/ICDAR.2007.4377017
Utpal Garain, S. K. Parui, T. Paquet, L. Heutte
This paper presents a pioneering study on automatic dating of handwritten manuscripts. Analysis of handwriting style forms the core of the dating method. Initially, it is hypothesized that a manuscript can be dated, to a certain level of accuracy, by looking at the way it is written. The hypothesis is then verified with real samples of known dates. A general framework is proposed for machine dating of handwritten manuscripts. Experiments on a database containing manuscripts of Gustave Flaubert (1821- 1880), the famous French novelist reports about 62% accuracy when manuscripts are dated within a range of five calendar years with respect to their exact year of writing.
{"title":"Machine Dating of Handwritten Manuscripts","authors":"Utpal Garain, S. K. Parui, T. Paquet, L. Heutte","doi":"10.1109/ICDAR.2007.4377017","DOIUrl":"https://doi.org/10.1109/ICDAR.2007.4377017","url":null,"abstract":"This paper presents a pioneering study on automatic dating of handwritten manuscripts. Analysis of handwriting style forms the core of the dating method. Initially, it is hypothesized that a manuscript can be dated, to a certain level of accuracy, by looking at the way it is written. The hypothesis is then verified with real samples of known dates. A general framework is proposed for machine dating of handwritten manuscripts. Experiments on a database containing manuscripts of Gustave Flaubert (1821- 1880), the famous French novelist reports about 62% accuracy when manuscripts are dated within a range of five calendar years with respect to their exact year of writing.","PeriodicalId":279268,"journal":{"name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122430564","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 an approach for writer identification using off-line Arabic handwriting. The proposed method explores the handwriting texture analysis by 2D discrete wavelet transforms using lifting scheme. A comparative evaluation between textural features extracted by 9 different wavelet transform functions was done. A modular multilayer perceptron classifier was used. Experiments have shown that writer identification accuracies reach best performance levels with an average rate of 95.68%. Experiments have been carried out using a database of 180 text samples. The chosen text was made to guarantee the involvement of the various internal shapes and letter locations within an Arabic subword.
{"title":"Arabic Handwriting Texture Analysis for Writer Identification Using the DWT-Lifting Scheme","authors":"S. Gazzah, N. Amara","doi":"10.1109/ICDAR.2007.62","DOIUrl":"https://doi.org/10.1109/ICDAR.2007.62","url":null,"abstract":"In this paper, we present an approach for writer identification using off-line Arabic handwriting. The proposed method explores the handwriting texture analysis by 2D discrete wavelet transforms using lifting scheme. A comparative evaluation between textural features extracted by 9 different wavelet transform functions was done. A modular multilayer perceptron classifier was used. Experiments have shown that writer identification accuracies reach best performance levels with an average rate of 95.68%. Experiments have been carried out using a database of 180 text samples. The chosen text was made to guarantee the involvement of the various internal shapes and letter locations within an Arabic subword.","PeriodicalId":279268,"journal":{"name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122328463","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}
Most studies about writer identification are based on English documents and to our knowledge no research has been reported on Farsi or Arabic documents. In this paper, we have proposed a method for off-line writer identification and verification based on Farsi handwriting, which is text-dependent. Based on the idea that has been presented in the previous studies, here we assume handwriting as texture image and after normalization step, the Gabor filters are applied to image and then new features are extracted. Substantially, the property of proposed method is using of the bank of Gabor filters which is appropriate for the structure of Farsi handwritten texts and vision system. Also, a new method for feature extraction from output of Gabor filters is proposed which is based on moments and nonlinear transform. In this paper, with definition a confidence criterion, a new method for writer verification is proposed. Evaluation of other methods and proposed method demonstrates that proposed method achieves better performance on Farsi handwritten from 40 peoples.
{"title":"A New Method for Writer Identification and Verification Based on Farsi/Arabic Handwritten Texts","authors":"F. Nejad, M. Rahmati","doi":"10.1109/ICDAR.2007.24","DOIUrl":"https://doi.org/10.1109/ICDAR.2007.24","url":null,"abstract":"Most studies about writer identification are based on English documents and to our knowledge no research has been reported on Farsi or Arabic documents. In this paper, we have proposed a method for off-line writer identification and verification based on Farsi handwriting, which is text-dependent. Based on the idea that has been presented in the previous studies, here we assume handwriting as texture image and after normalization step, the Gabor filters are applied to image and then new features are extracted. Substantially, the property of proposed method is using of the bank of Gabor filters which is appropriate for the structure of Farsi handwritten texts and vision system. Also, a new method for feature extraction from output of Gabor filters is proposed which is based on moments and nonlinear transform. In this paper, with definition a confidence criterion, a new method for writer verification is proposed. Evaluation of other methods and proposed method demonstrates that proposed method achieves better performance on Farsi handwritten from 40 peoples.","PeriodicalId":279268,"journal":{"name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126614275","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}
Document image segmentation algorithms primarily aim at separating text and graphics in presence of complex layouts. However, for many non-Latin scripts, segmentation becomes a challenge due to the characteristics of the script. In this paper, we empirically demonstrate that successful algorithms for Latin scripts may not be very effective for Indic and complex scripts. We explain this based on the differences in the spatial distribution of symbols in the scripts. We argue that the visual information used for segmentation needs to be enhanced with other information like script models for accurate results.
{"title":"On Segmentation of Documents in Complex Scripts","authors":"K. S. S. Kumar, S. Kumar, C. V. Jawahar","doi":"10.1109/ICDAR.2007.194","DOIUrl":"https://doi.org/10.1109/ICDAR.2007.194","url":null,"abstract":"Document image segmentation algorithms primarily aim at separating text and graphics in presence of complex layouts. However, for many non-Latin scripts, segmentation becomes a challenge due to the characteristics of the script. In this paper, we empirically demonstrate that successful algorithms for Latin scripts may not be very effective for Indic and complex scripts. We explain this based on the differences in the spatial distribution of symbols in the scripts. We argue that the visual information used for segmentation needs to be enhanced with other information like script models for accurate results.","PeriodicalId":279268,"journal":{"name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120954414","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}
Logical entity recognition in heterogeneous collections of document page images remains a challenging problem since the performance of traditional supervised methods degrades dramatically in case of many distinct layout styles. In this paper we present an unsupervised method where layout style information is explicitly used in both training and recognition phases. We represent the layout style, local features, and logical labels of physical regions of a document compactly by an ordered labeled X-Y tree. Style dissimilarity of two document pages is represented by the distance between their respective trees. During the training phase, document pages with true logical labels in training set are classified into distinct layout styles by unsupervised clustering. During the recognition phase, the layout style and logical entities of an input document are recognized simultaneously by matching the input tree to the trees in closest- matched layout style cluster of training set. Experimental results show that our algorithm is robust with both balanced and unbalanced style cluster sizes, zone over-segmentation, zone length variation, and variation in tree representations of the same layout style.
{"title":"Simultaneous Layout Style and Logical Entity Recognition in a Heterogeneous Collection of Documents","authors":"Siyuan Chen, Song Mao, G. Thoma","doi":"10.1109/ICDAR.2007.231","DOIUrl":"https://doi.org/10.1109/ICDAR.2007.231","url":null,"abstract":"Logical entity recognition in heterogeneous collections of document page images remains a challenging problem since the performance of traditional supervised methods degrades dramatically in case of many distinct layout styles. In this paper we present an unsupervised method where layout style information is explicitly used in both training and recognition phases. We represent the layout style, local features, and logical labels of physical regions of a document compactly by an ordered labeled X-Y tree. Style dissimilarity of two document pages is represented by the distance between their respective trees. During the training phase, document pages with true logical labels in training set are classified into distinct layout styles by unsupervised clustering. During the recognition phase, the layout style and logical entities of an input document are recognized simultaneously by matching the input tree to the trees in closest- matched layout style cluster of training set. Experimental results show that our algorithm is robust with both balanced and unbalanced style cluster sizes, zone over-segmentation, zone length variation, and variation in tree representations of the same layout style.","PeriodicalId":279268,"journal":{"name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127838342","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}
This paper proposes a novel online overlapped handwriting recognition system for mobile devices such as cellular phones. Users can input characters continuously without pauses on the single writing area. It has three features: small writing area, quick response and direct operations with handwritten gestures. Therefore, it is suitable for mobile devices such as cellular phones. The system realizes a new handwriting interface similar to touch-typing. We evaluated the system by two experiments: character recognition performance and text entry speed of Japanese sentences. Through these experiments we showed the effectiveness of the proposed system.
{"title":"Text Input System Using Online Overlapped Handwriting Recognition for Mobile Devices","authors":"Yojiro Tonouchi, A. Kawamura","doi":"10.1109/ICDAR.2007.243","DOIUrl":"https://doi.org/10.1109/ICDAR.2007.243","url":null,"abstract":"This paper proposes a novel online overlapped handwriting recognition system for mobile devices such as cellular phones. Users can input characters continuously without pauses on the single writing area. It has three features: small writing area, quick response and direct operations with handwritten gestures. Therefore, it is suitable for mobile devices such as cellular phones. The system realizes a new handwriting interface similar to touch-typing. We evaluated the system by two experiments: character recognition performance and text entry speed of Japanese sentences. Through these experiments we showed the effectiveness of the proposed system.","PeriodicalId":279268,"journal":{"name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127756317","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：