Vehicle License Plate Detection and Tilt Correction Based on HSI Color Model and SUSAN Corner Detector

Abstract

Detection and tilt correction of vehicle license plates are inevitable problems to be solved before developing Intelligent Transportation Systems. This paper describes a method of extraction of the vehicle license plate region from a vehicle image with tilt correction. The method consists of five distinct phases: segmenting color, labeling and filtering, correcting tilt, verifying candidate region, and segmenting license plate characters. Initially, an adaptive technique with labeling and filtering capability is utilized to select a statistical threshold value in the HSI color space for detecting candidate vehicle license plate regions. In this way the proposed method can overcome the limitation of the failure to detect a license plate when the vehicle body and license plate are similar colors. The slopes and tilt angles in both the horizontal and vertical directions of the skewed vehicle license plate are determined using the candidate corner points detected by the Smallest Univalue Segment Assimilating Nucleus corner detector, and the license plate region is rotated accordingly. Finally, a horizontal and vertical position histogram is employed to segment the candidate region into rows and constituent characters. The proposed tilt correction method is compared with the least square fitting with perpendicular offsets method and found to outperform results when the tilt angle gradually increases. 145 vehicle images were used for testing with different conditions and the results are presented to prove its efficiency and effectiveness.