CRFs and HCRFs Based Recognition for Off-Line Arabic Handwriting

被引：1

作者：

Elzobi, Moftah ^{[1
]}

Al-Hamadi, Ayoub ^{[1
]}

Dings, Laslo ^{[1
]}

El-etriby, Sherif ^{[2
]}

机构：

[1] Univ Magdeburg, Inst Informat Technol & Commun IIKT, POB 4210, D-39016 Magdeburg, Germany

[2] Umm Al Qura Univ, Mecca 21421, Saudi Arabia

来源：

ADVANCES IN VISUAL COMPUTING, PT II (ISVC 2015) | 2015年 / 9475卷

关键词：

D O I：

10.1007/978-3-319-27863-6_31

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 investigates the application of the probabilistic discriminative based Conditional Random Fields (CRFs) and its extension the hidden-states CRFs (HCRFs) to the problem of off-line Arabic handwriting recognition. A CRFs- and A HCRFs- based classifiers are built on top of an explicit word segmentation module using two different set of shape description features. A simple yet effective taxonomization technique is used to reduce the number of the class labels, and 3000 letter samples from IESK-arDB database are used for the training and 300 words are used for the evaluation. Experiments compare the performance of the CRFs to the HCRFs as well as to that of a generative based HMMs. Results indicate superiority of discriminative based approaches, where HCRFs achieved the best performance followed by CRFs.

引用

页码：337 / 346

页数：10

共 50 条

[31] Neural network language models for off-line handwriting recognition
Zamora-Martinez, F.
Frinken, V.
Espana-Boquera, S.
Castro-Bleda, M. J.
Fischer, A.
Bunke, H.
PATTERN RECOGNITION, 2014, 47 (04) : 1642 - 1652
[32] A comparison of recognition for off-line Myanmar handwriting and printed characters
Sandar, Khin
APSITT 2005: 6th Asia-Pacific Symposium on Information and Telecommunication Technologies, Proceedings, 2005, : 105 - 110
[33] Improvements in RWTH's system for off-line handwriting recognition
Kozielski, Michal
Doetsch, Patrick
Ney, Hermann
2013 12TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR), 2013, : 935 - 939
[34] Global word shape processing in off-line recognition of handwriting
Parisse, C
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1996, 18 (04) : 460 - 464
[35] Off-line jawi handwriting recognition using hamming classification
Facuity of Computer Science and Information Technology, University of Malaya, Kuala Lumpur, Malaysia
不详
Inf. Technol. J., 2009, 7 (971-981):
[36] A System for off-line Arabic Handwritten Word Recognition based on Bayesian Approach
Khemiri, Akram
Echi, Afef Kacem
Belaid, Abdel
Elloumi, Mourad
PROCEEDINGS OF 2016 15TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR), 2016, : 560 - 565
[37] Off-line Arabic handwritten characters recognition based on a Hidden Markov Models
Amrouch, M.
Elyassa, M.
Rachidi, A.
Mammass, D.
IMAGE AND SIGNAL PROCESSING, 2008, 5099 : 447 - 454
[38] An HMM based two-pass approach for off-line cursive handwriting recognition
Wang, WW
Brakensiek, A
Rigoll, G
ADVANCES IN MULTIMODAL INTERFACES - ICMI 2000, PROCEEDINGS, 2000, 1948 : 386 - 393
[39] Multilingual Off-line Handwriting Recognition in Real-world Images
Kozielski, Michal
Doetsch, Patrick
Hamdani, Mahdi
Ney, Hermann
2014 11TH IAPR INTERNATIONAL WORKSHOP ON DOCUMENT ANALYSIS SYSTEMS (DAS 2014), 2014, : 121 - 125
[40] Strategies for combining on-line and off-line information in an on-line handwriting recognition system
Gauthier, N
Artières, T
Dorizzi, B
Gallinari, P
SIXTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, PROCEEDINGS, 2001, : 412 - 416

← 1 2 3 4 5 →