Adaptive binarization: A new approach to license plate characters segmentation

Binarization of plate image is one of the major tasks in license plate recognition system (LPR). Many researchers have established various kinds of theories to reduce the degradation effects on a car license plate. However, most of these theories are not efficient in practice due to their expensive computational cost. This paper focuses on the binarization task of poor illumination in a practical commercial car license plates system. In proposed method, a mathematic morphology filter will be used as a low-pass filter to improve the illumination of license plate. To eliminate the impact of illumination, average filter, Gaussian filter and median filter are chosen to filter the plate image respectively. At last, convert the gray-scale image to binary image by the local threshold obtained from the convolved image with illumination compensation coefficient. Experimental results show that our method provides robust and low computational cost under various lightning or illumination effects.