Combining Multiple Feature Extraction Techniques for Handwritten Devnagari Character Recognition

被引:0
作者
Arora, Sandhya [1 ]
Bhattacharjee, Debotosh [2 ]
Nasipuri, Mita [2 ]
Basu, Dipak Kumar [3 ]
Kundu, Mahantapas [2 ]
机构
[1] Meghnad Saha Inst Technol, Dept CSE & IT, Kolkata 700107, India
[2] Jadavpur Univ, Dept Comp Sci & Engn, Kolkata 700032, West Bengal, India
[3] AICTE Emeritus Fellow, Kolkata, India
来源
IEEE REGION 10 COLLOQUIUM AND THIRD INTERNATIONAL CONFERENCE ON INDUSTRIAL AND INFORMATION SYSTEMS, VOLS 1 AND 2 | 2008年
关键词
Chain code features; Intersection features; Neural networks; Shadow features; Weighted majority voting technique;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In this paper we present an OCR for Handwritten Devnagari Characters. Basic symbols are recognized by neural classifier. We have used four feature extraction techniques namely, intersection, shadow feature, chain code histogram and straight tine fitting features. Shadow features are computed globally for character image while intersection features, chain code histogram features and line fitting features are computed by dividing the character image into different segments. Weighted majority voting technique is used for combining the classification decision obtained from four Multi Layer Perceptron(MLP) based classifier. On experimentation with a dataset of 4900 samples the overall recognition rate observed is 92.80% as we considered top five choices results. This method is compared with other recent methods for Handwritten Devnagari Character Recognition and it has been observed that this approach has better success rate than other methods.
引用
收藏
页码:454 / +
页数:2
相关论文
共 20 条
[1]  
ARONA S, 2006, INT C SIGN IM PROC I
[2]  
ARORA S, 2007, INT C COMP INT MULT
[3]  
ARORA S, 2006, CLASSIFICATION GRADI
[4]   Devnagari numeral recognition by combining decision of multiple connectionist classifiers [J].
Bajaj, R ;
Dey, L ;
Chaudhury, S .
SADHANA-ACADEMY PROCEEDINGS IN ENGINEERING SCIENCES, 2002, 27 (1) :59-72
[5]  
BASU S, 2005, HANDWRITTEN BANGLA A
[6]  
Bhattacharya U., 2005, P WORKSH LEARN ALG P, P1
[7]   A complete printed Bangla OCR system [J].
Chaudhuri, BB ;
Pal, U .
PATTERN RECOGNITION, 1998, 31 (05) :531-549
[8]   THINNING ALGORITHMS - A CRITIQUE AND A NEW METHODOLOGY [J].
DAVIES, ER ;
PLUMMER, APN .
PATTERN RECOGNITION, 1981, 14 (1-6) :53-63
[9]  
Freeman H., 1961, IRE T ELECTRON COMPU, V10, P260, DOI DOI 10.1109/TEC.1961.5219197
[10]  
Hanmandlu M., 2005, INT C COGN REC, P490