Improved Image Enhancement Method for License Plate Detection

Abstract

A novel approach based on vertical edge extraction is proposed for car plate detection. In order to manage the detection in low quality images (low contrast, blurred images etc), we first enhance image contrast at candidate regions for car plate. The vertical edges of the enhanced image are then extracted. Using morphological filtering, several candidates are constituted as license plate. Some distinctive features for car plate such as shape, aspect ratio is used to filter out false candidates. Using the correlation between the candidate regions and the model of car plate, the most probable region in the image is declared as the car plate. The experimental results on out-door images confirms the robustness of the proposed method against the severe imaging condition.