Slant Correction of Vehicle License Plate Based on Feature Point and Principal Component Analysis

Abstract

Slant Correction plays an important role in vehicle license plate automatic recognition system. In order to reduce or avoid adverse effects caused by noise disturbance and fragmentary frame of vehicle license plate, as well as speed up the computation, an approach based on feature point and principal component analysis (PCA) is presented. Feature points are considered as the edge of characters on the license plate, with a lined orderliness which reflects the slant angle of the plate. Firstly, a pretreatment process is carried out to extract the feature points of the plate, and the direction of the principal component, which is considered as the slant angle of the plate, is achieved through principal component analysis of the feature points, then the correction of the plate is accomplished. The experimental results demonstrate that, this method enjoys the advantages of being simple and less demanding in image quality and frame of license plate, and makes the correction of the plate easier and more precise compare to some other method such as Hough transform.