Secondary recognition method for easy-to-mix characters

The invention relates to a secondary recognition method for easy-to-mix characters, which is used for improving the recognition rate of handwritten characters. The method includes: performing refinement operation on the easy-to-mix character image to generate a target image with a fixed size; defining linear features, slope features and curvature features of the easy-to-mix character pairs ' 1 ',' (',') ', extracting feature vectors of the target image, and performing recognition and classification based on an SVM classifier; defining hole characteristics of the easy-to-mix character pairs '1 ' and ' 9 ', designing a classification algorithm based on the hole characteristics, and realizing secondary identification of ' 1 ' and ' 9 '; defining intersection point relative position characteristics of the easy-to-mix character pairs ' 4 ' and ' 6 ', designing a classification algorithm based on the intersection point relative position characteristics, and realizing secondary identification of ' 4 ' and ' 6 '; and