Improved rotation invariant template matching method using relative orientation codes

Orientation code is the quantization of pixel gradient orientation, which is illumination invariant, and has become an important template matching method. In order to improve accuracy and real time ability, we present conception of relative orientation code, and design template matching method based on relative orientation code. This method first selects candidate target points using relative orientation codes histogram matching, then calculate the rotation angle of candidate subimage and rotate the sub image, finally match the relative orientation codes in the sub image. The experiment show that this method is robust when the image is rotated by any angle, and the candidate points are selected and matched accurately, and the computing time is less than original method.