A new algorithm for license plate recognition based on improved edge detection and Mathematical morphology

This paper describes the advantages and disadvantages of current vehicle license plate location algorithms. To problems of inaccurating in Location of the vehicle plate, a method of image segmentation and extraction based on improved edge detection and Mathematical morphology was presented. In the first place, a series of color images were changed into gray images, secondly, through calculates the difference of each pixel and neighborhood pixels to buildup images´ edge, and it can make the license plate stand out; once again, by adding the original image of the the results map which enhanced edge image, and it uses Sobel operator to extract the edge of objects in image; then the algorithm applies the dilation and erosion mathematical morphology of binary images to get the the image smooth contour; finally, from locating the position area alignment in the X and Y directions to locating license plates, meanwhile, using the median filter and the dilation and erosion mathematical morphology, and template matching algorithm to recognize the license plate character. Because of the accuracy of the plate region extraction, the character can be extracted exactly from the plate region. It can improve the accuracy rate of the characters recognition. From the results of simulation, it is found that the new method proposed in this thesis is efficient.