A Recognition Algorithm for Chinese Chararcter Based on Minimum Distance Classifier

This paper investigates problems of image character recognition, especially Chinese character recognition. We herein recommend a novel recognition algorithm which is based on minimum distance classifier. Aiming at a subset of the features in a character that a human can typically see for the identification of typewritten Chinese characters, the algorithm attempts to work with two classes of feature extraction-structure and statistics. The statistic feature decides the primary class and the structure feature is used to identify Chinese characters. This paper also describes, analyzes and compares several other methods and results. Experimental results indicate that the recognition algorithm is effective for Chinese character in image.