CONF quelhas04a/IDIAP Fusion of Structural and Color Local Descriptors for Enhanced Object Recognition Quelhas, Pedro Odobez, Jean-Marc EXTERNAL http://publications.idiap.ch/attachments/papers/2004/quelhas_WIAMIS04.pdf PUBLIC http://publications.idiap.ch/index.php/publications/showcite/quelhas03c Related documents Proceedings IEEE WIAMIS 2004(5th International Workshop on Image Analysis for Multimedia Interactive Services,',','), 21-23 April, 2004, Lisboa, Portugal 2004 April 2004 IDIAP-RR 03-71 In this paper we study the behavior of local descriptor object recognition methods with respect to 3D geometric transformations and image resolution variations. As expected performance decreases with accentuated perspective and decrease in resolution. To improve performance and robustness, we propose a scheme to fuse color and gradient local descriptors. This approach is motivated by the discriminative power of color in man-made object recognition. The problem of color feature extraction is addressed as well as the considerations on the fusion process and steps to train such fusion. We used SOIL-47A database for experiments and shown a 7\% to 10\% relative improvement when compared with state-of-the-art gradient based descriptors. REPORT quelhas03c/IDIAP A Color and Gradient Local Descriptor Fusion Scheme For Object Recognition Quelhas, Pedro Odobez, Jean-Marc EXTERNAL http://publications.idiap.ch/attachments/reports/2003/rr03-71.pdf PUBLIC Idiap-RR-71-2003 2003 IDIAP Published in WIAMIS04 In this paper we study the behavior of local descriptor object recognition methods with respect to 3D geometric transformations and image resolution variations. As expected performance decreases with accentuated perspective and decrease in resolution. To improve performance and robustness, we propose a scheme to fuse color and gradient local descriptors. This approach is motivated by the discriminative power of color in man-made object recognition. The problem of color feature extraction is addressed as well as the considerations on the fusion process and steps to train such fusion. We used SOIL-47A database for experiments and shown a 7\% to 10\% relative improvement when compared with state-of-the-art gradient based descriptors.