Acquiring the Mapping Knowledge of Basic Elements Based on PSO in the Chinese Character Intelligent Information

In the system of Chinese character intelligent formation, the same basic element may have different position, size and shape in different Chinese characters. The transformation from basic elements to Chinese characters can be realized by affine transformation (AT), and a novel approach was proposed to acquire the AT coefficients of basic elements. The coefficients of linear transformation are taken as input, match is done between the Chinese character image and the basic element image after linear transformation. During the matching, the interested region is determined based on the structure of the Chinese character and normalized correlation coefficient (NCC) is used to measure the similarity of images. Then the coefficients of linear transformation are optimized by particle swarm optimization (PSO) algorithm, the position of best match are the coefficients of translation. 27533 Chinese characters in National Standards GB18030-2000 character set are taken as the experimental subject. Finally, the experimental processes and results were given in this paper.