Arabic OCR Using a Novel Hybrid Classification Scheme

被引：4

作者：

Hafiz, Abdul Mueed ^{[1
]}

Bhat, Ghulam Mohiuddin ^{[2
]}

机构：

[1] Univ Kashmir, Dept Elect & Commun, Srinagar 190006, Jammu & Kashmir, India

[2] Univ Kashmir, Univ Sci Instrumentat Ctr, Srinagar 190006, Jammu & Kashmir, India

来源：

JOURNAL OF PATTERN RECOGNITION RESEARCH | 2016年 / 11卷 / 01期

关键词：

Hidden Markov Models; Hybrid Classifiers; Arabic Text Recognition; IFN-ENIT Database;

D O I：

10.13176/11.711

中图分类号：

O1 [数学];

学科分类号：

0701 ; 070101 ;

摘要：

Hidden Markov Models or HMMs, are a relatively recent phenomenon for Arabic handwriting recognition. They are robust and efficient in classification. In this paper, an effort has been made to further boost the recognition capability of HMM Based Arabic Optical Character Recognition Systems, by using a two-tier hybrid classification scheme. The first tier consists of Part of Arabic Word or PAW, Based HMMs, and the second tier is a k-Nearest Neighbor Classifier or KNN Classifier. The second tier receives its inputs from the first tier. A second novel Hybrid Scheme is also examined. The recognition accuracies of the proposed schemes have been compared to contemporary techniques and they show an improvement in classification accuracy. HMMs have been implemented using the HTK Toolkit. The database used has been obtained from the IFN-ENIT Database of Arabic Words.

引用

页码：55 / 60

页数：6

共 26 条

[1]

AbdulKader A, 2008, LECT NOTES COMPUT SC, V4768, P70, DOI 10.1007/978-3-540-78199-8_5

[2]

Abed H.E., 2007, 9 INT S SIGN PROC IT, P1, DOI [10.1109/ISSPA.2007.4555529, DOI 10.1109/ISSPA.2007.4555529]

[3]

Ahmad I, 2015, PROC INT CONF DOC, P751, DOI 10.1109/ICDAR.2015.7333862

[4]

AlKhateeb Jawad H., 2009, 2009 IEEE International Conference on Signal and Image Processing Applications (ICSIPA 2009), P191, DOI 10.1109/ICSIPA.2009.5478620

[5]

Alkhoury I., 2012, GUIDE OCR ARABIC SCR, P255

[6]

[Anonymous], THE HTK BOOK V3 4

[7]

[Anonymous], 2012, GUIDE OCR ARABIC SCR

[8]

Azevedo WW, 2011, 2011 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), P843, DOI 10.1109/IJCNN.2011.6033309

[9] NEAREST NEIGHBOR PATTERN CLASSIFICATION [J].

COVER, TM ;

HART, PE .

IEEE TRANSACTIONS ON INFORMATION THEORY, 1967, 13 (01) :21-+

[10] Improving Offline Handwritten Text Recognition with Hybrid HMM/ANN Models [J].

Espana-Boquera, Salvador ;

Jose Castro-Bleda, Maria ;

Gorbe-Moya, Jorge ;

Zamora-Martinez, Francisco .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2011, 33 (04) :767-779

← 1 2 3 →