Train number recognition algorithm based on two cameras

The most critical technique in the train number detection process is the extraction and division of vehicle image. This paper introduces an intelligent detection system based on two cameras. First of all, on the basis of kalman prediction tracking algorithm, this paper puts forward a kind of collaborative tracking discriminant train number system, and determining the best Angle of the camera. To correct the collected images based on Hough transform and feature point projection., do binary processing according to a dynamic gray-level threshold of image, segment the image using local vertical projection method, intelligent matching the split character to the characters in the template library based on the Hamming short principle, and put forward a new method in the basis of that.