High-Speed Image Matching Based on Pair of Curvature of Edge Pixels by Optimized Selection

Abstract

This paper proposes a method to recognize a target image area that has free location and free inclination in an objective image. This method uses curvatures that are measured in two sizes of area as the matching key to improve the reliability of matching. Besides, if the only effective edge pixels can be used for matching, it is expected that the reliability and the computational cost may be improved because the number of registered template data decreases. To realize this function, the proposed method uses the genetic algorithm (GA) to determine the best combination of effective edge pixels for matching from the huge combinations of selected edge pixels. The experimental results show that the target image areas were searched successfully in spite of reducing the number of edge pixels. The averaged matching time was about only 0.1 second by using the proposed method.