DocumentCode :
1782482
Title :
A fast recognition scheme for off-line Bangla numerals
Author :
ul Masood, Md Raihan
Author_Institution :
Dept. of Comput. Sci. & Eng., Northern Univ. Bangladesh, Dhaka, Bangladesh
fYear :
2014
fDate :
8-10 March 2014
Firstpage :
350
Lastpage :
354
Abstract :
The requirement of Bangla character recognition has become one of the prime attentions among the current researchers due to the increase of automated systems and usage of hand held devices. This paper presents a novel approach to recognize handwritten bangla numerals and addresses a robust feature extraction scheme that spawns 23- dimensional features based on the numeral´s structure and topology. The recognition scheme is organized with a proposed decision tree that has been justified using entropy calculation. Considering inconsistency in individuals´ writing style and the presence of significant curves and loops, the proposed feature extraction method restricts to less dimensional features of each numeral from 14600 data samples. The recognition time of this scheme is much lower than the existing procedures, since the preprocessing tasks have been performed during down sampling operation. The quick response time 13.04 ms and the higher accuracy (96.82%) explore a new era for the proposed scheme of being implemented in Bangla numeral LeadPad toys.
Keywords :
character recognition; decision trees; feature extraction; image sampling; natural language processing; 23-dimensional features; Bangla character recognition; Bangla numeral LeadPad toys; automated systems; decision tree; down sampling operation; entropy calculation; fast off-line Bangla numeral recognition scheme; feature extraction method; hand held devices; individual writing style; numeral structure; numeral topology; quick response time; robust feature extraction scheme; Accuracy; Character recognition; Decision trees; Feature extraction; Handwriting recognition; Information technology; Time factors; Bangla Numeral; Character Recognition; Down Sampling; Entropy; Feature Extraction;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer and Information Technology (ICCIT), 2013 16th International Conference on
Conference_Location :
Khulna
Type :
conf
DOI :
10.1109/ICCITechn.2014.6997345
Filename :
6997345
Link To Document :
بازگشت