Pub Date : 2001-09-10DOI: 10.1109/ICDAR.2001.953901
V. Eglin, Antoine Gagneux
This paper presents a new approach to textual data labeling based on texture analysis. Texture is used here to show the impact of document composition on visual exploration. We demonstrate how textural properties are well adapted to typography characterization by categorizing document regions into visual text classes (such as headings, head- and footnotes, paragraphs, abstracts, etc.). We reference and classify different types of text fonts according to their visual aspect and the visual impression that emerges from the textual data. Experiments on a set of various document images show a good accuracy and robustness for our method.
{"title":"Visual exploration and functional document labeling","authors":"V. Eglin, Antoine Gagneux","doi":"10.1109/ICDAR.2001.953901","DOIUrl":"https://doi.org/10.1109/ICDAR.2001.953901","url":null,"abstract":"This paper presents a new approach to textual data labeling based on texture analysis. Texture is used here to show the impact of document composition on visual exploration. We demonstrate how textural properties are well adapted to typography characterization by categorizing document regions into visual text classes (such as headings, head- and footnotes, paragraphs, abstracts, etc.). We reference and classify different types of text fonts according to their visual aspect and the visual impression that emerges from the textual data. Experiments on a set of various document images show a good accuracy and robustness for our 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":"129572697","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.2001.953935
M. E. Dehkordi, N. Sherkat, Tony Allen
This paper describes an independent handwriting style classifier that has been designed to select the best recognizer for a given style of writing. For this purpose a definition of handwriting legibility has been defined and a method has been implemented that can predict this legibility. The technique consists of two phases. In the feature extraction phase, a set of 16 features is extracted from the image contour. These features have been selected from amongst a set of pre-recognition features as those features that contribute the most (95%) to a discriminant between legible and illegible words. In the classification phase, a Probability Neural Network based on Bayesian decision is introduced to predict the legibility of unknown handwriting using a Parzen method to estimate a class conditional density function from the available training data.
{"title":"Prediction of handwriting legibility","authors":"M. E. Dehkordi, N. Sherkat, Tony Allen","doi":"10.1109/ICDAR.2001.953935","DOIUrl":"https://doi.org/10.1109/ICDAR.2001.953935","url":null,"abstract":"This paper describes an independent handwriting style classifier that has been designed to select the best recognizer for a given style of writing. For this purpose a definition of handwriting legibility has been defined and a method has been implemented that can predict this legibility. The technique consists of two phases. In the feature extraction phase, a set of 16 features is extracted from the image contour. These features have been selected from amongst a set of pre-recognition features as those features that contribute the most (95%) to a discriminant between legible and illegible words. In the classification phase, a Probability Neural Network based on Bayesian decision is introduced to predict the legibility of unknown handwriting using a Parzen method to estimate a class conditional density function from the available training data.","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":"129687418","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.2001.953836
M. Parizeau, Alexandre Lemieux, Christian Gagné
This paper presents experiments that compare the performances of several versions of a regional-fuzzy representation (RFR) developed for cursive handwriting recognition (CHR). These experiments are conducted using a common neural network classifier namely a multilayer perceptron (MLP) trained with backpropagation. Results are given for isolated digits, isolated lower-case letters and lower-case letters extracted from phrases, from the Unipen database. Data set Train-R01/V07 is used for training while DevTest-R01/V02 is used for testing. The best overall representation yields recognition rates of respectively 97.0% and 85.6% for isolated digits and lower case, and 84.4% for lower-case extracted from phrases.
{"title":"Character recognition experiments using Unipen data","authors":"M. Parizeau, Alexandre Lemieux, Christian Gagné","doi":"10.1109/ICDAR.2001.953836","DOIUrl":"https://doi.org/10.1109/ICDAR.2001.953836","url":null,"abstract":"This paper presents experiments that compare the performances of several versions of a regional-fuzzy representation (RFR) developed for cursive handwriting recognition (CHR). These experiments are conducted using a common neural network classifier namely a multilayer perceptron (MLP) trained with backpropagation. Results are given for isolated digits, isolated lower-case letters and lower-case letters extracted from phrases, from the Unipen database. Data set Train-R01/V07 is used for training while DevTest-R01/V02 is used for testing. The best overall representation yields recognition rates of respectively 97.0% and 85.6% for isolated digits and lower case, and 84.4% for lower-case extracted from phrases.","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":"130311759","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.2001.953874
Yimei Ding, Masayuki Okada, F. Kimura, Y. Miyake
We describe the application of slant correction to handwritten Japanese address recognition. Horizontal strokes of Japanese characters in handwritten Japanese addresses often have a slant to the right upper direction. We propose an iterative modified 8-directional chain code method, that is adapted to slant estimation for these addresses. Recognition experiments for the IPTP cdrom2 database are performed to evaluate the effectiveness of slant correction. Comparative results show that based on slant correction, the accuracy of character segmentation and recognition are both improved, which lead to the accuracy improvement of address recognition.
{"title":"Application of slant correction to handwritten Japanese address recognition","authors":"Yimei Ding, Masayuki Okada, F. Kimura, Y. Miyake","doi":"10.1109/ICDAR.2001.953874","DOIUrl":"https://doi.org/10.1109/ICDAR.2001.953874","url":null,"abstract":"We describe the application of slant correction to handwritten Japanese address recognition. Horizontal strokes of Japanese characters in handwritten Japanese addresses often have a slant to the right upper direction. We propose an iterative modified 8-directional chain code method, that is adapted to slant estimation for these addresses. Recognition experiments for the IPTP cdrom2 database are performed to evaluate the effectiveness of slant correction. Comparative results show that based on slant correction, the accuracy of character segmentation and recognition are both improved, which lead to the accuracy improvement of address recognition.","PeriodicalId":277816,"journal":{"name":"Proceedings of Sixth International Conference on Document Analysis and Recognition","volume":"35 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":"128343936","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.2001.953793
Gregory N. Hullender
Many problems in recognition involve making linear combinations of results from various experts. Computing the coefficients can be expensive because a single test run can take many minutes, hours, or even days, and many values need to be evaluated to find an optimum. This paper describes an algorithm that can make a good approximation to the optimum value for a parameter in a single pass over the tuning data and also outlines methods for tuning several parameters at once.
{"title":"An efficient method for tuning handwriting parameters","authors":"Gregory N. Hullender","doi":"10.1109/ICDAR.2001.953793","DOIUrl":"https://doi.org/10.1109/ICDAR.2001.953793","url":null,"abstract":"Many problems in recognition involve making linear combinations of results from various experts. Computing the coefficients can be expensive because a single test run can take many minutes, hours, or even days, and many values need to be evaluated to find an optimum. This paper describes an algorithm that can make a good approximation to the optimum value for a parameter in a single pass over the tuning data and also outlines methods for tuning several parameters at once.","PeriodicalId":277816,"journal":{"name":"Proceedings of Sixth International Conference on Document Analysis and Recognition","volume":"3 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":"117092724","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.2001.953912
Cheng-Lin Liu, Masashi Koga, H. Fujisawa
Proposes a handwritten character string recognition method for Japanese mail address reading on very large vocabulary. The recognition is performed by classification-embedded lexicon matching based on over-segmentation. The lexicon contains 111,349 address phrases and is represented in a trie structure. In recognition, the input text line image is matched with all lexicon entries by beam search to obtain reliable character segmentation and retrieve valid phrases. A classifier is embedded in lexicon matching to select from a dynamic set the characters matched with a candidate pattern. The beam search and the character classification jointly enable accurate phrase identification in real time. In experiments on 3,589 live mail images, the proposed method achieved correct rate of 83.68% with error rate less than 1%.
{"title":"Lexicon-driven handwritten character string recognition for Japanese address reading","authors":"Cheng-Lin Liu, Masashi Koga, H. Fujisawa","doi":"10.1109/ICDAR.2001.953912","DOIUrl":"https://doi.org/10.1109/ICDAR.2001.953912","url":null,"abstract":"Proposes a handwritten character string recognition method for Japanese mail address reading on very large vocabulary. The recognition is performed by classification-embedded lexicon matching based on over-segmentation. The lexicon contains 111,349 address phrases and is represented in a trie structure. In recognition, the input text line image is matched with all lexicon entries by beam search to obtain reliable character segmentation and retrieve valid phrases. A classifier is embedded in lexicon matching to select from a dynamic set the characters matched with a candidate pattern. The beam search and the character classification jointly enable accurate phrase identification in real time. In experiments on 3,589 live mail images, the proposed method achieved correct rate of 83.68% with error rate less than 1%.","PeriodicalId":277816,"journal":{"name":"Proceedings of Sixth International Conference on Document Analysis and Recognition","volume":"14 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":"125936588","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.2001.953790
D. Shi, S. Gunn, R. Damper
Handwritten Chinese character recognition is one of the most difficult problems of pattern recognition. Since the majority of Chinese characters are made up from just a small set of primitive structures (radicals), this paper describes an approach to active radical modeling for such handwritten characters. The most significant characteristic of our method is that radicals can be found robustly without stroke extraction, and the principal variations of the radical can be encoded in a small number of parameters. In the training phase, the example radicals are represented by manually-labeled 'landmark' points. Then a small number of principal components of the eigenvectors are calculated to capture the main variation of the training examples from the mean radical. In the matching phase, each radical model is fitted to the image evidence by adjusting the shape parameters in terms of chamfer distance minimization. Initial experiments are conducted on 1,100 loosely-constrained Chinese character categories written by 200 different writers. The correct matching rate is 95.8%, showing that our radical modeling is effective and capable of forming a sound basis for handwritten Chinese character recognition.
{"title":"Active radical modeling for handwritten Chinese characters","authors":"D. Shi, S. Gunn, R. Damper","doi":"10.1109/ICDAR.2001.953790","DOIUrl":"https://doi.org/10.1109/ICDAR.2001.953790","url":null,"abstract":"Handwritten Chinese character recognition is one of the most difficult problems of pattern recognition. Since the majority of Chinese characters are made up from just a small set of primitive structures (radicals), this paper describes an approach to active radical modeling for such handwritten characters. The most significant characteristic of our method is that radicals can be found robustly without stroke extraction, and the principal variations of the radical can be encoded in a small number of parameters. In the training phase, the example radicals are represented by manually-labeled 'landmark' points. Then a small number of principal components of the eigenvectors are calculated to capture the main variation of the training examples from the mean radical. In the matching phase, each radical model is fitted to the image evidence by adjusting the shape parameters in terms of chamfer distance minimization. Initial experiments are conducted on 1,100 loosely-constrained Chinese character categories written by 200 different writers. The correct matching rate is 95.8%, showing that our radical modeling is effective and capable of forming a sound basis for handwritten Chinese character recognition.","PeriodicalId":277816,"journal":{"name":"Proceedings of Sixth International Conference on Document Analysis and Recognition","volume":"62 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":"127238913","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.2001.953914
Jun Zhou, C. Suen, Ke Liu
The proposed feedback-based approach is implemented in two steps. In the first step, segmentation is done according to the structural features between the connected components in the legal amounts. In the second step, a feedback process is introduced to re-segment the parts that could not be identified in the first step. Then a multiple neural network classifier is used to verify the re-segmentation result. The confidence value produced by the classifier is used to determine the best segmentation points. This approach is tested on a CENPARMI database and the result indicates that the correct segmentation rate increased by 13.4% from the previous approach.
{"title":"A feedback-based approach for segmenting handwritten legal amounts on bank cheques","authors":"Jun Zhou, C. Suen, Ke Liu","doi":"10.1109/ICDAR.2001.953914","DOIUrl":"https://doi.org/10.1109/ICDAR.2001.953914","url":null,"abstract":"The proposed feedback-based approach is implemented in two steps. In the first step, segmentation is done according to the structural features between the connected components in the legal amounts. In the second step, a feedback process is introduced to re-segment the parts that could not be identified in the first step. Then a multiple neural network classifier is used to verify the re-segmentation result. The confidence value produced by the classifier is used to determine the best segmentation points. This approach is tested on a CENPARMI database and the result indicates that the correct segmentation rate increased by 13.4% from the previous approach.","PeriodicalId":277816,"journal":{"name":"Proceedings of Sixth International Conference on Document Analysis and Recognition","volume":"52 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113974147","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.2001.953941
H. Kang, Seong-Whan Lee
Only a few studies have been conducted on how to select multiple classifiers from the pool of available classifiers for showing good performance. The selection problem of classifiers on how to select or how many to select still remains an important issue. In this paper, provided that the number of selected classifiers is constrained in advance, a number of selection criteria are proposed and applied to the construction of multiple classifiers. All the sets of classifiers are examined by the selection criteria under the constraint of the number of selected classifiers, and then some of those sets are selected as the candidates of multiple classifier systems. The multiple classifier system candidates were evaluated by the experiments recognizing UCI handwritten numerals.
{"title":"Experimental results on the construction of multiple classifiers recognizing handwritten numerals","authors":"H. Kang, Seong-Whan Lee","doi":"10.1109/ICDAR.2001.953941","DOIUrl":"https://doi.org/10.1109/ICDAR.2001.953941","url":null,"abstract":"Only a few studies have been conducted on how to select multiple classifiers from the pool of available classifiers for showing good performance. The selection problem of classifiers on how to select or how many to select still remains an important issue. In this paper, provided that the number of selected classifiers is constrained in advance, a number of selection criteria are proposed and applied to the construction of multiple classifiers. All the sets of classifiers are examined by the selection criteria under the constraint of the number of selected classifiers, and then some of those sets are selected as the candidates of multiple classifier systems. The multiple classifier system candidates were evaluated by the experiments recognizing UCI handwritten numerals.","PeriodicalId":277816,"journal":{"name":"Proceedings of Sixth International Conference on Document Analysis and Recognition","volume":"43 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":"122850062","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.2001.953929
Masashi Koga, Ryuji Mine, H. Sako, H. Fujisawa
We propose a new method to recognize the machine-printed monetary amount based on two-dimensional segmentation and bottom-up parsing. In conventional segmentation-based methods, the system segments the image only along the direction of the character line. This new method segments the image both horizontally and vertically, and extracts candidates of character segments correctly if there are many noises or characters are fragmented. A parsing module detects the optimal sequence of candidate segments using linguistic knowledge. In our method, a context-free grammar describes the linguistic constraints in the monetary amounts. We devised a new bottom-up parsing technique that interprets the results of character classification of the two-dimensionally segmented sub-images. We tested the validity of the new method using 1,314 images, and found that it improves the recognition accuracy significantly.
{"title":"A recognition method of machine-printed monetary amounts based on the two-dimensional segmentation and the bottom-up parsing","authors":"Masashi Koga, Ryuji Mine, H. Sako, H. Fujisawa","doi":"10.1109/ICDAR.2001.953929","DOIUrl":"https://doi.org/10.1109/ICDAR.2001.953929","url":null,"abstract":"We propose a new method to recognize the machine-printed monetary amount based on two-dimensional segmentation and bottom-up parsing. In conventional segmentation-based methods, the system segments the image only along the direction of the character line. This new method segments the image both horizontally and vertically, and extracts candidates of character segments correctly if there are many noises or characters are fragmented. A parsing module detects the optimal sequence of candidate segments using linguistic knowledge. In our method, a context-free grammar describes the linguistic constraints in the monetary amounts. We devised a new bottom-up parsing technique that interprets the results of character classification of the two-dimensionally segmented sub-images. We tested the validity of the new method using 1,314 images, and found that it improves the recognition accuracy significantly.","PeriodicalId":277816,"journal":{"name":"Proceedings of Sixth International Conference on Document Analysis and Recognition","volume":"4 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":"130150978","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：