Individuality of Bangla numerals

Author

Halder, Chayan ; Paul, J. ; Roy, Kaushik

Author_Institution

Dept. of Comput. Sci., West Bengal State Univ., Kolkata, India

fYear

2012

fDate

27-29 Nov. 2012

Firstpage

264

Lastpage

268

Abstract

This paper presents analysis of individuality of handwritten Bangla numerals. It has a great prospect in Writer Identification, Writer Verification, Forensic Science etc. After collecting and extracting characters from filled in forms, 400 dimensional feature vectors is computed based on gradient of the images. A total of 450 documents were used for this work. In our experiment we have used LIBLINEAR classifier of WEKA environment. We have computed and analyzed the Individuality of each numeral and observed that the numeral 5 has the most individuality property than other numerals and 0 has the least. We have also done the writer identification with all the numerals and obtained 96.5% accuracy with all writers.

Keywords

gradient methods; handwriting recognition; natural language processing; LIBLINEAR classifier; WEKA environment; forensic science; gradient methods; handwritten Bangla numerals; writer identification; writer verification; Accuracy; Educational institutions; Electronic mail; Feature extraction; Intelligent systems; Support vector machines; Writing; Bangla Handwriting Analysis; Individuality of Handwriting; WEKA; Writer Identification;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Systems Design and Applications (ISDA), 2012 12th International Conference on

Conference_Location

Kochi

ISSN

2164-7143

Print_ISBN

978-1-4673-5117-1

Type

conf

DOI

10.1109/ISDA.2012.6416548

Filename

6416548