Automatic writer identification framework for online handwritten documents using character prototypes

被引:41
作者
Tan, Guo Xian [1 ,2 ]
Viard-Gaudin, Christian [2 ]
Kot, Alex C. [1 ]
机构
[1] Nanyang Technol Univ, Coll Engn, Singapore, Singapore
[2] Univ Nantes, Ecole Polytech, CNRS, IRCCyN,UMR 6597, F-44035 Nantes, France
关键词
Writer identification; Information retrieval; Online handwriting; Fuzzy c-means; Allographs; RECOGNITION; FEATURES;
D O I
10.1016/j.patcog.2008.12.019
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper proposes an automatic text-independent writer identification framework that integrates an industrial handwriting recognition system, which is used to perform an automatic segmentation of an online handwritten document at the character level. Subsequently, a fuzzy c-means approach is adopted to estimate statistical distributions of character prototypes on an alphabet basis. These distributions model the unique handwriting styles of the writers. The proposed system attained an accuracy of 99.2% when retrieved from a database of 120 writers. The only limitation is that a minimum length of text needs to be present in the document in order for sufficient accuracy to be achieved. We have found that this minimum length of text is about 160 characters or approximately equivalent to 3 lines of text. In addition, the discriminative power of different alphabets on the accuracy is also reported. (C) 2009 Elsevier Ltd. All rights reserved.
引用
收藏
页码:3313 / 3323
页数:11
相关论文
共 42 条
[31]   A Study of Designing Compact Classifiers using Deep Neural Networks for Online Handwritten Chinese Character Recognition [J].
Du, Jun ;
Hu, Jin-Shui ;
Zhu, Bo ;
Wei, Si ;
Dai, Li-Rong .
2014 22ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2014, :2950-2955
[32]   Online Arabic Handwritten Character Recognition using Online-Offline Feature Extraction and Back-Propagation Neural Network [J].
Ramzi, Amal ;
Zahary, Ammar .
2014 1ST INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES FOR SIGNAL AND IMAGE PROCESSING (ATSIP 2014), 2014, :350-355
[33]   Text-Independent Online Writer Identification Using Hidden Markov Models [J].
Wu, Yabei ;
Lu, Huanzhang ;
Zhang, Zhiyong .
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2017, E100D (02) :332-339
[34]   Writer identification using hand-printed and non-hand-printed questioned documents [J].
Kam, M ;
Lin, EW .
JOURNAL OF FORENSIC SCIENCES, 2003, 48 (06) :1391-1395
[35]   Online Kanji Characters Based Writer Identification Using Sequential Forward Floating Selection and Support Vector Machine [J].
Hasan, Md Al Mehedi ;
Shin, Jungpil ;
Maniruzzaman, Md .
APPLIED SCIENCES-BASEL, 2022, 12 (20)
[36]   Writer identification system for pre-segmented offline handwritten Devanagari characters using k-NN and SVM [J].
Shaveta Dargan ;
Munish Kumar ;
Anupam Garg ;
Kutub Thakur .
Soft Computing, 2020, 24 :10111-10122
[37]   Chinese Character-level Writer Identification using Path Signature Feature, DropStroke and Deep CNN [J].
Yang, Weixin ;
Jin, Lianwen ;
Liu, Manfei .
2015 13TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR), 2015, :546-550
[38]   Improved Deep Convolutional Neural Network For Online Handwritten Chinese Character Recognition using Domain-Specific Knowledge [J].
Yang, Weixin ;
Jin, Lianwen ;
Xie, Zecheng ;
Feng, Ziyong .
2015 13TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR), 2015, :551-555
[39]   A deep learning framework for historical manuscripts writer identification using data-driven features [J].
Bennour, Akram ;
Boudraa, Merouane ;
Siddiqi, Imran ;
Al-Sarem, Mohammad ;
Al-Shaby, Mohammad ;
Ghabban, Fahad .
MULTIMEDIA TOOLS AND APPLICATIONS, 2024, 83 (33) :80075-80101
[40]   AUTOMATIC LINE-LEVEL SCRIPT IDENTIFICATION FROM HANDWRITTEN DOCUMENT IMAGES - A REGION-WISE CLASSIFICATION FRAMEWORK FOR INDIAN SUBCONTINENT [J].
Obaidullah, Sk Md ;
Halder, Chayan ;
Santosh, K. C. ;
Das, Nibaran ;
Roy, Kaushik .
MALAYSIAN JOURNAL OF COMPUTER SCIENCE, 2018, 31 (01) :63-84