License Plate Location Detection Algorithm based on Two-dimensional Gamma Function

摘要

For vehicle images under uneven illumination, a two-dimensional gamma function adaptive brightness correction algorithm is proposed to reduce the influence of uneven illumination and license plate positioning is realized. Firstly, the image is converted from RGB to HSI and the three components are separated. Tonal H remains unchanged and saturation S is stretched by contrast. Multi-scale Gaussian function is used to extract the illumination component of the brightness I and two-dimensional gamma function is constructed for adaptive brightness correction to obtain a new brightness component TI. The three components are combined to obtain a new HSI color image. Then, the vehicle image after correction is preprocessed and sobel edge detection is also carried out. Finally, the license plate location is realized by using the geometric features of the license plate. The experimental results show that this method can effectively locate the vehicle images both at night and under uneven illumination.