Property‐based shadow detection and removal method for licence plate image

Abstract

Shadow detection and removal is a classic research in the field of image processing. This work aims to address the problem of shadow detection and removal for licence plate. The shadow detection and removal method based on inherent properties of licence plate is presented in this study. First, an S–V-channel-property-based shadow detection algorithm is investigated to extract the background-shaded area of licence plate. Afterwards, a shadow edge location algorithm is proposed to detect the complete shadow edge. Then, the shadow is removed on H, S, and V channels with different strategies, respectively. Also, a filter-based median filtering algorithm is employed to remove the pseudo-edge. Finally, the proposed method is verified through comparing with other generic shadow detection and removal methods quantitatively and qualitatively.