How to tell the difference between a cat and a dog?
Nima Razavi, Golnoosh Samei, Masoud Alipour, Ali Farhadi · International Journal of Imaging Systems and Technology · 2006
Abstract The aim of this work is to present a method in computer vision for model‐based object recognition by integration of texture, color, and partial silhouette matching cues. As a test problem, a challenging task of distinguishing between cats and dogs are proposed. No condition is imposed on the images. In spite of high intraclass variability of two classes (especially dogs), accuracy rate of over 92% is achieved. A novel method for integration of color information to textures is also presented. © 2007 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 16, 234–239, 2006