Feature Extraction of Chinese Characters Based on ASM Algorithm

In Chinese Calligraphy education, the computer-based evaluation on Chinese handwriting is one of the problems in the field of computer intelligent education. In this study, the method of feature comparison is first proposed in the process of computer-based evaluation on Chinese handwriting, focusing on automatically and accurately extracting the features of Chinese characters. Then, the key technologies applied in feature extraction of Chinese character were analyzed. It discussed the representation of features, aligns training samples, and reduces dimensions by principal component analysis, established local gray-scale model, and converged the gray-scale information of target feature points through statistical analysis. The experimental results show that the accuracy of the algorithm is 93.84%.