노이즈 제거 알고리즘을 이용한 효율적인 자동차 번호판 검출에 관한 연구

Abstract

The extraction of License plate is an important stage in vehicle license plate recognition for Vehicle Plate Recognition System(VPRS). This paper presents a real time and robust method of the extraction of licence plate. The license plate of the car consists of several characters, so the plate area contains lots of edge information. But the background of the car image holds much edge information too. This paper notice two facts. One is that the background areas around the license plate mainly include some horizontal edges. The other is that the edges in the background are mainly long curves and noises, whereas the edges in the plate area cluster together and produce intense texture feature. If only the vertical edges are extracted from the car image and most of the background edges are removed, the plate area will be left out distinctly in the whole edge image. Thus this paper propose to extract the license plate in its vertical edge image as in the following four stages, image enhancement, vertical edge extraction, background curve and noise removing, and finally car plate search and segmentation. The car images captured in gloomy days or dim nights make it difficult to extract car plate. Therefore it is important to enhance the car images firstly. Then this paper extract out the vertical edges of the car image using Sobel operator and remove most of the background and noise edges by the proposed algorithm, and finally search the license plate region in the residual edge image and segment the plate out from the original car image. The proposed method is applied to many experimental images with 256 gray levels and the results are compared with those of other methods. The results show that the proposed method is better than others.