A Fast License Plate Segmentation and Recognition Method Based on the Modified Template Matching

Abstract

Character segmentation is an important step in a LPR system, this paper presents a new method for character segmentation and recognition, correcting the image of license plate which uses the improved method of Hough Transform, then employs the normalization method to segment the characters of the license plate and finally utilizes a modified template matching method to recognize the characters of the license plate. The result of the experiment shows that the method presented in the paper is easy and feasible, faster in recognizable speed, performs well in segmentation, and is valuable in practical application. Keywords-License plate recognition; Projection; Templates matching; Character segmentation