Rectification Technology Of Image Geometric Distortion And Application In Vehicle License Recognition System

Utilizing the rectification technology of geometric distortion in vehicle license recognition system based on image processing and close-range photogrammetry theory is important in increasing system reliability. The vehicle license recognition system is an important research project that use computer vision and pattern recognition technology in intelligent traffic control regions. The license image has geometric distortion because of several factors, such as camera location, camera distortion etc. It is difficult to recognize the license. To this problem a series of image rectification procedure which utilize geometric rectification theory in vehicle license recognition system are pointed out: We first locate vehicle license and execute the edge detection and binary conversion, then proceed calibration in which we use two calibration scheme looking for control point coordinate, one based on the Hough transformation, the other based on image analysis method, and finally realize image correction in geometrical transform and bilinear gray interpolation method. This thesis introduces the method of image rectification step by step, illustrates the theory of calibration and the method about accurate location of control point in detail. The result of experimentation affirms that this method is effective to the image of vehicle license.