Acquire the Affine Transformation Coefficients in the Chinese Character Intelligent Formation

Abstract

In the Chinese character intelligent formation, the same basic element has different position, size and shape in different Chinese characters. The transformation from the basic element to the Chinese character can be realized by affine transformation, and a novel approach was proposed to acquire the transformation coefficients of basic elements. The interested region was determined based on the structure of Chinese character, scale invariant and location invariant was extracted with SIFT features; meanwhile, rotation invariant was removed. The matched points was determined by Euclidean distance of eigenvectors, the best of three pairs non-collinear points were selected by using particle swarm optimization (PSO) algorithm which take normalized correlation coefficient as fitness function. 27533 Chinese characters in National Standards GB18030-2000 character set were taken as the experimental subject. Finally, the experimental processes and results were given in this paper.