Image Fast Template Matching Algorithm Based on Projection and Sequential Similarity Detecting

Abstract

Image matching is an important topic in the field of image processing, and it is widely used in image registration and image fusion. An image fast template matching algorithm based on projection and sequential similarity detecting is proposed. The algorithm employs the strategy of image template matching that is from sketch matching to detail matching. Firstly the real-time images are projected to obtain one dimension data, and it is employed for sketch matching with one dimension data from reference image. Secondly sequential similarity detecting principle is used for the detail matching employing the points with larger similarity in the sketch matching. The experimental results showed that the proposed algorithm was efficient and faster than conventional image template matching algorithms.