Object detection based on fast template matching through adaptive partition search

In computer vision, object detection is one of the most researched topics. The goal of object detection is to detect all instances of objects from a known class, such as people, cars or faces in an image. Object detection uses the extracted features and learning algorithms to detect and recognize objects. In this paper, we propose a robust object detection method based on fast template matching. We apply an adaptive partition search to divide the target image properly. During this process, we can make efficiently match each template into the sub-images based on distortion measures. Finally, the template image is updated appropriately by an adaptive template algorithm. Experimental results show that the proposed method is very efficient and fast for object detection.