DocumentCode :
3059144
Title :
Recognition of Handwritten Kannada Numerals
Author :
Sharma, N. ; Pal, U. ; Kimura, F.
Author_Institution :
Indian Stat. Inst., Kolkata
fYear :
2006
fDate :
18-21 Dec. 2006
Firstpage :
133
Lastpage :
136
Abstract :
This paper deals with a quadratic classifier based scheme for the recognition of off-line handwritten numerals of Kannada, an important Indian script. The features used in the classifier are obtained from the directional chain code information of the contour points of the characters. The bounding box of a character is segmented into blocks and the chain code histogram is computed in each of the blocks. Here we have used 64 dimensional and 100 dimensional features for a comparative study on the recognition accuracy of our proposed system. This chain code features are fed to the quadratic classifier for recognition. We tested our scheme on 2300 data samples and obtained 97.87% and 98.45% recognition accuracy using 64 dimensional and 100 dimensional features respectively, from the proposed scheme using five-fold cross-validation technique.
Keywords :
feature extraction; handwriting recognition; handwritten character recognition; image classification; image segmentation; chain code histogram; contour points; feature extraction; handwriting recognition; handwritten Kannada numerals; image segmentation; quadratic classifier; Automation; Character recognition; Computer vision; Handwriting recognition; Histograms; Natural languages; Neural networks; Pattern recognition; Testing; Training data;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Information Technology, 2006. ICIT '06. 9th International Conference on
Conference_Location :
Bhubaneswar
Print_ISBN :
0-7695-2635-7
Type :
conf
DOI :
10.1109/ICIT.2006.77
Filename :
4273171
Link To Document :
بازگشت