License plate location method based on edge detection and mathematical morphology

Abstract

The license plate location plays a key role in the license plate recognition system. The quality of the positioning result determines the subsequent license plate character recognition. For the image based on edge detection, it is difficult to detect the license plate area for the discoloration or serious pollution of the license plate. Therefore, a license plate location method based on edge detection and mathematical morphology is proposed. Firstly, the image preprocessing of the license plate includes graying and binarization. Then, the Sobel operator edge detection is performed according to the binarized license plate image. The Sobel operator has moderate sensitivity to the edge and is suitable for the extraction of the license plate edge. Finally, On the result of Sobel operator processing, the mathematical morphology of corrosion, expansion, opening and closing operations are performed to obtain the final license plate location.