Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)最新文献_第9页

Online Handwritten Kanji Recognition Based on Inter-stroke Grammar 基于笔画间语法的在线手写汉字识别

Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Pub Date : 2007-09-23 DOI: 10.1109/ICDAR.2007.202

Ikumi Ota, Ryo Yamamoto, Shinji Sako, S. Sagayama

{"title":"Online Handwritten Kanji Recognition Based on Inter-stroke Grammar","authors":"Ikumi Ota, Ryo Yamamoto, Shinji Sako, S. Sagayama","doi":"10.1109/ICDAR.2007.202","DOIUrl":"https://doi.org/10.1109/ICDAR.2007.202","url":null,"abstract":"This paper presents a new approach to online recognition of handwritten Kanji characters focusing on their hierarchical structure. Stochastic context-free grammar (SCFG) is introduced to represent the Kanji character generating process in combination with Hidden Markov Models (HMM) representing Kanji substrokes and to improve the recognition accuracy of important and frequently used Kanji characters in which inter-stroke relative positions play important roles. Combining the stroke likelihood and the relative-position likelihood between character-parts in the parsing process is expected to compensate their ambiguities. By modeling relative positions and share the models across distinct Kanji categories, a small training data can yield effective results and enables us to recognize Kanji simply by defining the SCFG rules to represent their structures without training data. Experimental results on an online handwritten Kanji database from JAIST (Japan Advanced Institute of Science and Technology) showed significant improvements in the recognition rates of some important Kanji with relatively fewer strokes and also showed little difference between the trained- and the non-trained Kanji in recognition rates.","PeriodicalId":279268,"journal":{"name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","volume":"27 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":"127849247","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}

引用次数: 15

Robust Binarization for Video Text Recognition 视频文本识别的鲁棒二值化

Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Pub Date : 2007-09-23 DOI: 10.1109/ICDAR.2007.222

Z. Saidane, Christophe Garcia

引用次数: 42

Transform-Invariance in Local Averaging Classifier for Handwritten Digit Pattern Recognition 手写体数字模式识别局部平均分类器的变换不变性

Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Pub Date : 2007-09-23 DOI: 10.1109/ICDAR.2007.253

Seiji Hotta

引用次数: 1

On Computing Strength of Evidence for Writer Verification 作者验证的证据计算强度研究

Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Pub Date : 2007-09-23 DOI: 10.1109/ICDAR.2007.193

H. Srinivasan, Shrivardhan Kabra, Chen Huang, S. Srihari

{"title":"On Computing Strength of Evidence for Writer Verification","authors":"H. Srinivasan, Shrivardhan Kabra, Chen Huang, S. Srihari","doi":"10.1109/ICDAR.2007.193","DOIUrl":"https://doi.org/10.1109/ICDAR.2007.193","url":null,"abstract":"The problem of writer verification is to make a decision of whether or not two handwritten documents are written by the same person. Providing a strength of evidence for any such decision is an integral part of the writer verification problem. The strength of evidence should incorporate (i) The amount of information compared in each of the two documents (line/half page/full page etc.), (ii) The nature of content present in the document (same/different content), (iii) Features used for comparison and (iv) The error rate of the model used for making the decision. This paper describes the statistical model used for writer verification and also introduces a mathematical formulation to include the above four mentioned parameters, for calculating strength of evidence of same/different writer. The statistical model uses Gamma and Gaussian densities to parametrically model the distance space distribution arising from comparing ensemble of pairs of documents. The strength of evidence is mapped to a 9-point qualitative scale for the decision; one that is often used by questioned document examiners. Experiments and results show that with increase in information content from just a single word to a full page of document, the verification accuracy of the model increases.","PeriodicalId":279268,"journal":{"name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","volume":"85 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":"129168963","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}

引用次数: 17

A Human-Centric Off-Line Signature Verification System 以人为本的离线签名验证系统

Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Pub Date : 2007-09-23 DOI: 10.1109/ICDAR.2007.13

H. Coetzer, R. Sabourin

引用次数: 17

Recognition of Fragmented Characters Using Multiple Feature-Subset Classifiers 基于多特征子集分类器的碎片字符识别

Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Pub Date : 2007-09-23 DOI: 10.1109/ICDAR.2007.214

Chien-Hsing Chou, Chien-Yang Guo, F. Chang

引用次数: 1

A View on the Past and Future of Character and Document Recognition 文字与文件识别的过去与未来

Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Pub Date : 2007-09-23 DOI: 10.1109/ICDAR.2007.39

H. Fujisawa

引用次数: 20

Document Processing via Trained Morphological Operators 通过训练形态学算子的文档处理

Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Pub Date : 2007-09-23 DOI: 10.1109/ICDAR.2007.104

N. Hirata

引用次数: 7

Recognition of Broken Characters from Historical Printed Books Using Dynamic Bayesian Networks 利用动态贝叶斯网络识别历史印刷书籍中的断字

Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Pub Date : 2007-09-23 DOI: 10.1109/ICDAR.2007.213

Laurence Likforman-Sulem, M. Sigelle

引用次数: 12

An Indexing Method for Graphical Documents 图形文档的索引方法

Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Pub Date : 2007-09-23 DOI: 10.1109/ICDAR.2007.55

S. Tabbone, Daniel Zuwala

引用次数: 15