2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)最新文献_第10页

Layout and Perspective Distortion Independent Recognition of Captured Chinese Document Image 捕获中文文档图像的布局和透视畸变独立识别

2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) Pub Date : 2017-11-01 DOI: 10.1109/ICDAR.2017.102

Yanwei Wang, Yuefang Sun, Changsong Liu

引用次数: 4

Machine Learning vs Deterministic Rule-Based System for Document Stream Segmentation 机器学习与基于确定性规则的文档流分割系统

2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) Pub Date : 2017-11-01 DOI: 10.1109/ICDAR.2017.332

Ahmed Hamdi, J. Voerman, Mickaël Coustaty, Aurélie Joseph, V. P. d'Andecy, J. Ogier

引用次数: 7

A Case Study of the Relationship between Local Pen Action and Three Dimensional Shapes of Handwritten Strokes 笔的局部动作与手写笔画三维形状关系的个案研究

2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) Pub Date : 2017-11-01 DOI: 10.1109/ICDAR.2017.389

Yoshinori Akao, Yoshiyasu Higashikawa

{"title":"A Case Study of the Relationship between Local Pen Action and Three Dimensional Shapes of Handwritten Strokes","authors":"Yoshinori Akao, Yoshiyasu Higashikawa","doi":"10.1109/ICDAR.2017.389","DOIUrl":"https://doi.org/10.1109/ICDAR.2017.389","url":null,"abstract":"In this article, we performed a case study of the relationship between local pen action and three dimensional shapes of handwritten strokes on paper sheet. The purpose of the study is to enrich the knowledge effective for forensic handwriting examination. Samples for analysis were one Japanese Hiragana character written by one participant. Online and offline handwritings were captured simultaneously by using ink pen tablet. The type of pen was ballpoint pen, and characters were written on paper for plain copy placed on the tablet. The position and pen pressure information were captured at 200 Hz. The precision of pen position was 0.25 mm, and the pen pressure information was at 15 bit. Experimental results showed that the depth information of overall area of character was related with the density of handwritten strokes. On the other hand, the local shape of handwritten stroke was considered to be related with local pen action. As the pen pressure increased, the depth and the width of handwritten strokes increased. In addition, the influence of pen pressure spread widely around handwritten strokes. However, the local shape was not only dependent on pen pressure but also on pen speed.","PeriodicalId":433676,"journal":{"name":"2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)","volume":"143 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128767643","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: 0

A Framework for Document Specific Error Detection and Corrections in Indic OCR 索引OCR中文档特定错误检测和更正的框架

2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) Pub Date : 2017-11-01 DOI: 10.1109/ICDAR.2017.308

Rohit Saluja, D. Adiga, Ganesh Ramakrishnan, P. Chaudhuri, Mark James Carman

{"title":"A Framework for Document Specific Error Detection and Corrections in Indic OCR","authors":"Rohit Saluja, D. Adiga, Ganesh Ramakrishnan, P. Chaudhuri, Mark James Carman","doi":"10.1109/ICDAR.2017.308","DOIUrl":"https://doi.org/10.1109/ICDAR.2017.308","url":null,"abstract":"In this paper, we present a framework for assisting word-level corrections in Indic OCR documents by incorporating the ability to identify, segment and combine partially correct word forms. The partially correct word forms themselves may be obtained from corrected parts of the document itself and auxiliary sources such as dictionaries and common OCR character confusions. Our framework updates a domain dictionary and learns OCR specific n-gram confusions from the human feedback on the fly. The framework can also leverage consensus between outputs of multiple OCR systems on the same text as an auxiliary source for dynamic dictionary building. Experimental evaluations confirm that for highly inflectional Indian languages, matching partially correct word forms an result in significant reduction in the amount of manual input required for correction. Furthermore, significant gains are observed when the consolidated output of multiple OCR systems is employed as an auxiliary source of information. We have corrected over 1100 pages (13 books) in Sanskrit, 190 pages (1 book) in Marathi, 50 pages (part of a book) in Hindi and 1000 pages (12 books) in English using our framework. We present a book-wise analysis of improvement in required human interaction for these Languages.","PeriodicalId":433676,"journal":{"name":"2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128779813","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: 4

Qumran Letter Restoration by Rotation and Reflection Modified PixelCNN 基于旋转和反射的Qumran字母复原

2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) Pub Date : 2017-11-01 DOI: 10.1109/ICDAR.2017.14

L. Uzan, N. Dershowitz, Lior Wolf

引用次数: 4

A Comprehensive Survey on Handwriting and Computerized Graphology 手写体与电脑化笔迹学的综合调查

2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) Pub Date : 2017-11-01 DOI: 10.1109/ICDAR.2017.107

Afnan H. Garoot, Maedeh Safar, C. Suen

引用次数: 12

Benchmarking Keypoint Filtering Approaches for Document Image Matching 文档图像匹配的基准点过滤方法

2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) Pub Date : 2017-11-01 DOI: 10.1109/ICDAR.2017.64

Emilien Royer, J. Chazalon, Marçal Rusiñol, F. Bouchara

引用次数: 6

Online Handwritten Mongolian Word Recognition Using a Novel Sliding Window Method with Recurrent Neural Networks 基于递归神经网络滑动窗口的在线手写体蒙古语单词识别

2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) Pub Date : 2017-11-01 DOI: 10.1109/ICDAR.2017.39

Ji Liu, Long-Long Ma, Jian Wu

{"title":"Online Handwritten Mongolian Word Recognition Using a Novel Sliding Window Method with Recurrent Neural Networks","authors":"Ji Liu, Long-Long Ma, Jian Wu","doi":"10.1109/ICDAR.2017.39","DOIUrl":"https://doi.org/10.1109/ICDAR.2017.39","url":null,"abstract":"Because of the conglutinated characteristic of Mongolian words, it's difficult to realize online handwritten Mongolian word recognition with high recognition accuracy based on segmentation-based strategy. Meanwhile, as the vocabulary of Mongolian words is large, using a segmentation-free method with deep bidirectional long short term memory(DBLSTM) network is more suitable. We design a 5 bidirectional hidden level DBLSTM network for online handwritten Mongolian word recognition. This paper mainly proposes a novel sliding window method which selects frames with different intervals to enhance recognition rate. The novel method can generate hundreds of sequence data for each sample, while only one sequence data is generated using ordinary sliding window method. More sequence data and more abundant sequence information are helpful to raise the recognition rate. We evaluated the recognition performance on our online handwritten Mongolian database with 925 classes. The proposed method achieves the word level recognition rate of 89.24% with PCA feature extractor and best path decoding, compared to that of 88.45% using ordinary sliding window method. Further, several well trained DBLSTM models based on the proposed method are combined to vote the output, finally, the word-level recognition raises to 90.35%.","PeriodicalId":433676,"journal":{"name":"2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)","volume":"7 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116739859","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: 2

Learning Structural Loss Parameters on Graph Embedding Applied on Symbolic Graphs 符号图嵌入中结构损失参数的学习

2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) Pub Date : 2017-11-01 DOI: 10.1109/ICDAR.2017.268

H. Jarraya, O. R. Terrades, J. Lladós

引用次数: 0

Landscape or Portrait? The Impact of Page Orientation on the Understandability of Scientific Posters 横向还是纵向?页向对科学海报可理解性的影响

2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) Pub Date : 2017-11-01 DOI: 10.1109/ICDAR.2017.376

Marc Beck, Seyyed Saleh Mozaffari Chanijani, S. S. Bukhari, A. Dengel

引用次数: 1