Research Of License Plate Region Segmentation Based On Texture Analysis

In the view of early vision, texture is an intuitive. According to the license plate region texture and the Gabor wavelets filters character, which is a good simulation of the human vision, we investigate the license plate region segmentation based on texture analysis.The followings are the major tasks in the thesis:1) In space domain, 24 Gabor wavelets filters are constructed. According to the optimal band of Gabor wavelets filter choosing criterion, we choose the 12 Gabor wavelets filters, which are verified the information of the 12 filtered images included above 98% all the information of the all filtered images by the experiments' results.2) To increase the difference, the non-linear transform function is used. The each pixel is computed by the average of a window's energy, which is Gabor wavelets energy and the input feature vector of unsupervised classification.3) K-mean clustering algorithm is used classification. The category is two, according to the object and the experience knowledge. The one is the license plate region and the other is the background region.4) We use the erosion and dilation of mathematical morphology to determine the license plate region.