Recognition of handprinted Thai characters using the cavity features of character based on neural network

Abstract

This paper describes a method of cavity features and neural network for recognizing handprinted Thai characters. The recognition process is implemented using mathematical morphology to detect the cavity features of patterns, and learning to classify by neural network. The stage of recognition divided into three stages. First, the handprinted Thai characters are segmented from the sentence into three different level groups. Then, the cavity features of each handprinted Thai character are detected, and counted the numbers by the Euler number method. Finally, uses the majority area of the cavity features for computed the feature codes of the characters in each class. These codes are trained by neural network for learning in the classification characters.