In the paper, support vector machine is presented to detection for vehicle’ s overlap, which has stronger generalization ability than the algorithm based on the empirical risk, such as artificial neural network. In the process of detection for vehicle’ s overlap, principal component analysis is used to extract the features and reduce the dimension of features. Then, detection model for vehicle’ s overlap based on SVM is constructed. We collected the 220 vehicle images including the overlapped vehicle images and non-overlapped vehicle images as the experimental data. The experimental results indicate that the accuracy of detection the vehicle’ s overlap by SVM is higher than that of BP neural network.

This paper presents an effective license plate location algorithm, which employs Mathematical morphology to extract the number plate from the complicated-background image. Mathematical morphology is a new method which is applied in this filed of image treatments and pattern recognition. The basic mind is using structure element to measure and extract corresponding Shape of image and finally in reach to the aim of image analysis and recognition.