Abstract—Handwritten Character Recognition (HCR) is very important in academic and production fields. The recognition system can be either online or offline. There is a large scope for optical character recognition on hand written documents. India is a multilingual and multi script country, where eighteen official scripts are accepted and have over hundred regional languages. Recognition of unconstrained hand written Indian scripts is difficult because of the presence of numerals, vowels, consonants, vowel modifiers and compound characters. In this paper we have implemented to recognize the unconstrained handwritten Kannada numeral characters and have proposed the projection distance metrics method for numeral recognition and General Regression Neural Network (GRNN) for the classification of the character image.
Index Terms—Feature Extraction Method (FEM), Dataset Size (DS) and Classification Method (CM).
The authors are with Dept. of Computer Science and Engineering, Canara Engineering College, Bantwal, India
Cite: Basappa B. Kodada and Shivakumar K. M., "Unconstrained Handwritten Kannada Numeral Recognition," International Journal of Information and Electronics Engineering vol. 3, no. 2, pp. 230-232, 2013.