Haar features based handwritten character recognition system for Tulu script

Abstract

Automatic recognition of handwritten characters from scanned images helps to convert characters in an image into convenient editable and readable form. Tulu is a south Indian Dravidian language with rich set of handwritten patterns. This paper presents an approach to recognize the Tulu script using automatic character recognition mechanism. The recognition of handwritten Tulu characters is based on the AdaBoost algorithm using Haar features. Finally, recognized characters are mapped into an equivalent editable document of Kannada characters. Hence, make it to readable for the next generation by digital technology.