Methods of distinguishing contours and describing key points when comparing color images

Abstract

This paper discusses methods of using color information in solving problems of image comparison and the recognition and tracking of objects in a closed space. These problems are characteristic of the computer-vision systems of mobile robots. Methods of distinguishing contours on the basis of the Cumani operator are discussed, as well as of detecting key points, using a color method based on the difference of Gaussians. A new method is proposed for constructing descriptors of the key points, based on the color tensor. Experiments show an increase in the efficiency of the indicated methods by 10–15%, with a close-to-threefold increase of the processing time.