G. Vamvakas, B. Gatos, Sergios Petridis, N. Stamatopoulos
In this paper, we present an off-line methodology for isolated Greek handwritten character recognition based on efficient feature extraction followed by a suitable feature vector dimensionality reduction scheme. Extracted features are based on (i) horizontal and vertical zones, (ii) the projections of the character profiles, (Hi) distances from the character boundaries and (iv) profiles from the character edges. The combination of these types of features leads to a 325- dimensional feature vector. At a next step, a dimensionality reduction technique is applied, according to which the dimension of the feature space is lowered down to comprise only the features pertinent to the discrimination of characters into the given set of letters. In this paper, we also present a new Greek handwritten database of 36,960 characters that we created in order to measure the performance of the proposed methodology.
{"title":"An Efficient Feature Extraction and Dimensionality Reduction Scheme for Isolated Greek Handwritten Character Recognition","authors":"G. Vamvakas, B. Gatos, Sergios Petridis, N. Stamatopoulos","doi":"10.1109/ICDAR.2007.49","DOIUrl":"https://doi.org/10.1109/ICDAR.2007.49","url":null,"abstract":"In this paper, we present an off-line methodology for isolated Greek handwritten character recognition based on efficient feature extraction followed by a suitable feature vector dimensionality reduction scheme. Extracted features are based on (i) horizontal and vertical zones, (ii) the projections of the character profiles, (Hi) distances from the character boundaries and (iv) profiles from the character edges. The combination of these types of features leads to a 325- dimensional feature vector. At a next step, a dimensionality reduction technique is applied, according to which the dimension of the feature space is lowered down to comprise only the features pertinent to the discrimination of characters into the given set of letters. In this paper, we also present a new Greek handwritten database of 36,960 characters that we created in order to measure the performance of the proposed methodology.","PeriodicalId":279268,"journal":{"name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","volume":"4 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":"123805034","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}
Huaigu Cao, R. Prasad, P. Natarajan, Ehry MacRostie
In this paper we present a robust multi-pass page segmentation algorithm. The first pass uses a modified smearing algorithm and the second pass performs a hybrid of bottom-up and top-down segmentation on the output of the first pass. Unlike traditional approaches, the bottom-up and top-down steps are based on primitive results of a smearing based page segmentation algorithm. Therefore, "split" and "merge" processes start with text blocks that are mostly true text blocks but a few of them are either touching or broken. We present experimental results on newspaper and journal documents from different languages to demonstrate the robustness and language independence of our approach.
{"title":"Robust Page Segmentation Based on Smearing and Error Correction Unifying Top-down and Bottom-up Approaches","authors":"Huaigu Cao, R. Prasad, P. Natarajan, Ehry MacRostie","doi":"10.1109/ICDAR.2007.225","DOIUrl":"https://doi.org/10.1109/ICDAR.2007.225","url":null,"abstract":"In this paper we present a robust multi-pass page segmentation algorithm. The first pass uses a modified smearing algorithm and the second pass performs a hybrid of bottom-up and top-down segmentation on the output of the first pass. Unlike traditional approaches, the bottom-up and top-down steps are based on primitive results of a smearing based page segmentation algorithm. Therefore, \"split\" and \"merge\" processes start with text blocks that are mostly true text blocks but a few of them are either touching or broken. We present experimental results on newspaper and journal documents from different languages to demonstrate the robustness and language independence of our approach.","PeriodicalId":279268,"journal":{"name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","volume":"26 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":"116551389","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 a general method to segment and recognize pairs of touching and overlapping symbols. The method, whose purpose is to lead to a generic approach in future works, is based on the evaluation of several segmentation candidates produced by grouping elements of an over-segmentation. A pure general method would involve a high number of segmentation candidates. An adaptive introduction of heuristics, representing the knowledge dedicated to the applicative domain, allows to decrease this number. We have largely tested the method on pairs of touching and overlapping digits.
{"title":"A General Method of Segmentation-Recognition Collaboration Applied to Pairs of Touching and Overlapping Symbols","authors":"C. Renaudin","doi":"10.1109/ICDAR.2007.11","DOIUrl":"https://doi.org/10.1109/ICDAR.2007.11","url":null,"abstract":"In this paper, we present a general method to segment and recognize pairs of touching and overlapping symbols. The method, whose purpose is to lead to a generic approach in future works, is based on the evaluation of several segmentation candidates produced by grouping elements of an over-segmentation. A pure general method would involve a high number of segmentation candidates. An adaptive introduction of heuristics, representing the knowledge dedicated to the applicative domain, allows to decrease this number. We have largely tested the method on pairs of touching and overlapping digits.","PeriodicalId":279268,"journal":{"name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","volume":"30 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":"122385804","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 some Thai documents, a single text line of a document page may contain both Thai and English scripts. For the optical character recognition (OCR) of such a document page it is better to identify, at first, Thai and English script portions and then to use individual OCR system of the respective scripts on these identified portions. In this paper, a SVM based method is proposed for identification of word-wise printed English and Thai scripts from a single line of a document page. Here, at first, the document is segmented into lines and then lines are segmented into character groups (words). In the proposed scheme, we identify the script of the individual character group combining different character features obtained from structural shape, profile, component overlapping information, topological properties, water reservoir concept etc. Based on the experiment on 6110 data we obtained 99.36% script identification accuracy from the proposed scheme.
{"title":"SVM Based Scheme for Thai and English Script Identification","authors":"S. Chanda, O. R. Terrades, U. Pal","doi":"10.1109/ICDAR.2007.237","DOIUrl":"https://doi.org/10.1109/ICDAR.2007.237","url":null,"abstract":"In some Thai documents, a single text line of a document page may contain both Thai and English scripts. For the optical character recognition (OCR) of such a document page it is better to identify, at first, Thai and English script portions and then to use individual OCR system of the respective scripts on these identified portions. In this paper, a SVM based method is proposed for identification of word-wise printed English and Thai scripts from a single line of a document page. Here, at first, the document is segmented into lines and then lines are segmented into character groups (words). In the proposed scheme, we identify the script of the individual character group combining different character features obtained from structural shape, profile, component overlapping information, topological properties, water reservoir concept etc. Based on the experiment on 6110 data we obtained 99.36% script identification accuracy from the proposed scheme.","PeriodicalId":279268,"journal":{"name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","volume":"159 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":"122557337","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}
We propose a document analysis method, which extracts text and layout information from document files of various formats. This method analyzes the page description language (PDL) data generated from a printed document. By converting the document to PDL data, this method can handle various document formats. Graphic elements such as text objects, image objects, and path objects in the PDL data are analyzed to extract text and layout information (character size, character position, and table position). By applying OCR to the image objects and the path objects, text images in source documents and vectorized font characters in engineering drawings are converted to text. Moreover, tables in various documents are detected by analyzing path objects. Therefore, it is possible to extract the full content information from document files of various formats as long as the document is printable.
{"title":"Text and Layout Information Extraction from Document Files of Various Formats Based on the Analysis of Page Description Language","authors":"T. Hirano, Y. Okano, Yasuhiro Okada, Fumio Yoda","doi":"10.1109/ICDAR.2007.242","DOIUrl":"https://doi.org/10.1109/ICDAR.2007.242","url":null,"abstract":"We propose a document analysis method, which extracts text and layout information from document files of various formats. This method analyzes the page description language (PDL) data generated from a printed document. By converting the document to PDL data, this method can handle various document formats. Graphic elements such as text objects, image objects, and path objects in the PDL data are analyzed to extract text and layout information (character size, character position, and table position). By applying OCR to the image objects and the path objects, text images in source documents and vectorized font characters in engineering drawings are converted to text. Moreover, tables in various documents are detected by analyzing path objects. Therefore, it is possible to extract the full content information from document files of various formats as long as the document is printable.","PeriodicalId":279268,"journal":{"name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","volume":"28 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":"122819325","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 presents a novel syntactic symbol recognition approach to the vector based symbol recognition problem. Different from existing syntactic approaches, which usually describe the geometric relations among primitives, our method formulates a new model to describe the geometric information of a primitive with respect to the whole symbol object based on mathematical analysis. The mathematical model is theoretically rotation and scale invariant and experiments show its accuracy for vector based symbol recognition.
{"title":"A New Syntactic Approach to Graphic Symbol Recognition","authors":"Yu Yajie, Wan Zhang, Wenyin Liu","doi":"10.1109/ICDAR.2007.26","DOIUrl":"https://doi.org/10.1109/ICDAR.2007.26","url":null,"abstract":"This paper presents a novel syntactic symbol recognition approach to the vector based symbol recognition problem. Different from existing syntactic approaches, which usually describe the geometric relations among primitives, our method formulates a new model to describe the geometric information of a primitive with respect to the whole symbol object based on mathematical analysis. The mathematical model is theoretically rotation and scale invariant and experiments show its accuracy for vector based symbol recognition.","PeriodicalId":279268,"journal":{"name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","volume":"19 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":"122957897","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 presents a new framework for in-depth analysis of the performance of layout analysis methods. Contrary to existing approaches aimed at evaluation or benchmarking, the proposed framework provides detailed information at various levels that can be used by method developers to identify specific problems and improve their work. Complex layouts are supported as well as the flexible configuration of goal-oriented performance analysis scenarios. The comparison of segmentation results against the ground truth is performed in a very efficient way based on a decomposition of any region shape into an interval-based description. The framework has been validated using the dataset and method results of the ICDAR2005 Page Segmentation Competition.
{"title":"Performance Analysis Framework for Layout Analysis Methods","authors":"A. Antonacopoulos, D. Bridson","doi":"10.1109/ICDAR.2007.207","DOIUrl":"https://doi.org/10.1109/ICDAR.2007.207","url":null,"abstract":"This paper presents a new framework for in-depth analysis of the performance of layout analysis methods. Contrary to existing approaches aimed at evaluation or benchmarking, the proposed framework provides detailed information at various levels that can be used by method developers to identify specific problems and improve their work. Complex layouts are supported as well as the flexible configuration of goal-oriented performance analysis scenarios. The comparison of segmentation results against the ground truth is performed in a very efficient way based on a decomposition of any region shape into an interval-based description. The framework has been validated using the dataset and method results of the ICDAR2005 Page Segmentation Competition.","PeriodicalId":279268,"journal":{"name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","volume":"28 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114102385","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}
We report a hierarchical blind script identifier for 11 different Indian scripts. An initial grouping of the 11 scripts is accomplished at the first level of this hierarchy. At the subsequent level, we recognize the script in each group. The various nodes of this tree use different feature-classifier combinations. A database of 20,000 words of different font styles and sizes is collected and used for each script. Effectiveness of Gabor and Discrete Cosine Transform features has been independently evaluated using nearest neighbor, linear discriminant and support vector machine classifiers. The minimum and maximum accuracies obtained, using this hierarchical mechanism, are 92.2% and 97.6%, respectively.
{"title":"A Blind Indic Script Recognizer for Multi-script Documents","authors":"P. Pati, A. Ramakrishnan","doi":"10.1109/ICDAR.2007.2","DOIUrl":"https://doi.org/10.1109/ICDAR.2007.2","url":null,"abstract":"We report a hierarchical blind script identifier for 11 different Indian scripts. An initial grouping of the 11 scripts is accomplished at the first level of this hierarchy. At the subsequent level, we recognize the script in each group. The various nodes of this tree use different feature-classifier combinations. A database of 20,000 words of different font styles and sizes is collected and used for each script. Effectiveness of Gabor and Discrete Cosine Transform features has been independently evaluated using nearest neighbor, linear discriminant and support vector machine classifiers. The minimum and maximum accuracies obtained, using this hierarchical mechanism, are 92.2% and 97.6%, respectively.","PeriodicalId":279268,"journal":{"name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","volume":"24 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":"121866020","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. Wachenfeld, Stefan Fleischer, Hans-Ulrich Klein, Xiaoyi Jiang
The lower the resolution of a given text is, the more difficult it becomes to segment it into single characters. The resolution of screen-rendered text can be very low. This paper focuses on smoothed screen-rendered text of very low resolution with typical x-heights of 4 to 7 pixels which is much lower than in other low resolution OCR situations. We propose a recognition-based segmentation algorithm which makes use of over segmentation by dynamic programming, candidate rating by single character classifiers and a graph based search algorithm for an optimal cut sequence. The algorithm is described in detail and experimental results are presented which show the performance on example screen- shot images taken from the public Screen-Word database.
{"title":"Segmentation of Very Low Resolution Screen-Rendered Text","authors":"S. Wachenfeld, Stefan Fleischer, Hans-Ulrich Klein, Xiaoyi Jiang","doi":"10.1109/ICDAR.2007.229","DOIUrl":"https://doi.org/10.1109/ICDAR.2007.229","url":null,"abstract":"The lower the resolution of a given text is, the more difficult it becomes to segment it into single characters. The resolution of screen-rendered text can be very low. This paper focuses on smoothed screen-rendered text of very low resolution with typical x-heights of 4 to 7 pixels which is much lower than in other low resolution OCR situations. We propose a recognition-based segmentation algorithm which makes use of over segmentation by dynamic programming, candidate rating by single character classifiers and a graph based search algorithm for an optimal cut sequence. The algorithm is described in detail and experimental results are presented which show the performance on example screen- shot images taken from the public Screen-Word database.","PeriodicalId":279268,"journal":{"name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","volume":"45 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":"129942683","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. Imdad, S. Bres, V. Eglin, C. Rivero-Moreno, H. Emptoz
Writer recognition is considered as a difficult problem to solve due to variations found in the writing, even from the same writer. In this paper, steered Hermite features are used to identify writer from a written document. We will show that steered Hermite features are highly useful for text images because they extract lot of information, notably for data characterized by oriented features, curves and segments. The algorithm we propose here, first calculates the steered Hermite features of the images which are then passed on to support vector machine for training and testing. The base of tests consists of sample of some lines of writings (five at most) of primarily diversified writings of authors from IAM database. With the proposed algorithm based on steered Hermite features, we were able to achieve an accuracy of around 83% percent for a set of 30 authors with non overlapping images of written text.
{"title":"Writer Identification Using Steered Hermite Features and SVM","authors":"A. Imdad, S. Bres, V. Eglin, C. Rivero-Moreno, H. Emptoz","doi":"10.1109/ICDAR.2007.271","DOIUrl":"https://doi.org/10.1109/ICDAR.2007.271","url":null,"abstract":"Writer recognition is considered as a difficult problem to solve due to variations found in the writing, even from the same writer. In this paper, steered Hermite features are used to identify writer from a written document. We will show that steered Hermite features are highly useful for text images because they extract lot of information, notably for data characterized by oriented features, curves and segments. The algorithm we propose here, first calculates the steered Hermite features of the images which are then passed on to support vector machine for training and testing. The base of tests consists of sample of some lines of writings (five at most) of primarily diversified writings of authors from IAM database. With the proposed algorithm based on steered Hermite features, we were able to achieve an accuracy of around 83% percent for a set of 30 authors with non overlapping images of written text.","PeriodicalId":279268,"journal":{"name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","volume":"1 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":"129445724","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：