CHARACTER SEGMENTATION AND RECOGNITION METHOD

摘要

A character segmentation and recognition method, which is used for resolving the problems that the prior-art segmentation method is low in capacity for recognizing characters under a complex background and poor in contamination interference resistance. The method comprises: collecting image data to obtain an image to be recognized; locating a character-row candidate area on the image to be recognized; acquiring preset character-row prior information, wherein the character-row prior information comprises the number of characters, a character pitch and a character size; acquiring a corresponding segmentation point template according to the character-row prior information; acquiring reliability of the segmentation point template on different positions when the character-row candidate area is traversed; determining a position with the highest reliability as an optimum segmentation position; segmenting the character-row candidate area according to the segmentation point template and the optimum segmentation position to obtain a plurality of single character areas; and performing character recognition on the single character area to obtain a corresponding recognition result.