Holistic recognition of handwritten Tamil words

Author

Subramaniam, T. ; Pal, Umapada ; Premaretne, H. ; Kodikara, Nihal

Author_Institution

Dept. of Comput. Sci., Eastern Univ. Sri Lanka, Trincomalee, Sri Lanka

fYear

2012

fDate

Nov. 30 2012-Dec. 1 2012

Firstpage

165

Lastpage

169

Abstract

In this paper, we describe a writer independent method for recognizing offline unconstrained handwritten Tamil words/strings. Touching and overlapping are main bottleneck of handwriting recognition and to overcome this, we adopted a holistic approach here. To handle various handwritings of different individuals, at first, some pieces of preprocessing work are done on an input word. Next, Gabor based features are computed on the processed word. These Gabor features along with other geometric features of the word image are then fed to an SVM classifier for recognition. In our experimental study, we have used 4270 samples (collected from the class of 217 country names) written in Tamil and obtained 86.36% recognition rate.

Keywords

Gabor filters; feature extraction; handwritten character recognition; image classification; natural language processing; support vector machines; Gabor based features; SVM classifier; geometric features; handwritten Tamil words; holistic recognition; offline unconstrained handwritten Tamil string recognition; offline unconstrained handwritten Tamil word recognition; overlapping; touching; writer independent method; Accuracy; Character recognition; Feature extraction; Gabor filters; Handwriting recognition; Shape; Support vector machines; Gabor features; Handwritten Character Recognition; Holistic approach; SVM; Unconstrained Tamil word recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Emerging Applications of Information Technology (EAIT), 2012 Third International Conference on

Conference_Location

Kolkata

Print_ISBN

978-1-4673-1828-0

Type

conf

DOI

10.1109/EAIT.2012.6407887

Filename

6407887