Research On License Plate Location And Slant Correction In Vehicle License Plate Recognition System

The Automatic License Plate Recognition System is a specific computer vision system based on the specific goals of the vehicle license. It is composed with vehicle plate capture,vehicle plate recognition module, database management and data transfer through net etc. The vehicle plate recognition module is composed with vehicle plate location, character segmentation and character recognition.The algorithm of vehicle plate location and license plate slant correction method combining mathematical morphology is studied systemically in this paper.First, the paper introduces the license plate image pre-processing techniques and methods in detail. It has handled the license plate location image with greyscale, used piecewise-linear gray-scale transformation to enhance the image contrast, furthermore, used the improved Otsu method to change greyscale image into two-value image. To get a better edge image, adopted the improved anti-noise dilate-type operator for edge detection, and morphological filtering smooth images, the use of these technical methods help to improve the accuracy of the ALPR system.Locate the plate is the first step of the ALPR system,whose accuracy directly affects the success of the character recognition result. Firstly, an algorithm applied to license plate location based on mathematics morphology is introduced, using it to process image pretreatment. Secondly, area morphology combined with its elemental calculation is used to realize the license plate location and locate roughly. The opening operation and closing operation of morphology are used to wipe off noise. Finally the boundary of license plate is located through projection, the license plate frame and up-low rivet have been removed. Namely, the fine plate region is definitely located. Experiment results show that such method is not only simple and fast, but also robust. Image skew correction is one of the key technologies in 1icense plate recognition. According to the Radon transformation, the corresponding correction methods are presented to three inclined ways. First, the edge of the plate picture is detected by the related operation of mathematical morphology. Next, lossless rotation correction is performed to the tilt plate to the horizontal line, and bilinear interpolation offset correction is made to the plate that is tilt to the vertical line. Experimental results show that the proposed method is valid.This paper has made use of the Matlab software to carry out the license plate location and skew correction. According to many actual experiments, we obtain a satisfactory result. It is useful for the following steps about the character segmentation and recognition.