Dr. Tian Wins Best Paper Award at PCM
Dr. Qi Tian recently recieved the best paper award for his paper "A Novel Feature Descriptor Exploring Anisotropy and Non-uniformity" at the Pacific-rim Conference on Multimedia held in Nanjing, China on December 13-16, 2013. This work is a collaboration with the Institute of Computing Technology at the Chinese Academy of Science.
See below for details on the paper that won the award.
Z. Mao, Y. Zhang, and Q. Tian, “A Novel Feature Descriptor Exploring Anisotropy and Non-uniformity, ” Best Paper Award, Pacific-rim Conference on Multimedia, Nanjing, China, Dec. 13-16, 2013.
Matching keypoints across images is the base of numerous Computer Vision applications, which is often done with local feature descriptors. Hancrafted descriptors such as SIFT and SURF are still established leaders in the field since they are discriminative as well as robust. In this paper, we introduce a novel COGE descriptor, a simple yet effective method for keypoint description. By exploiting the anisotropy and the non-uniformity of the underlying gradient distributions, the proposed COGE is highly discriminative and robust. In addition, COGE contains only 480/240/120 bits and can be matched by using Hamming distance, making it ideal for mobile applications. To evaluate the performance of COGE, a comprehensive comparison against SIFT, SURF, ORB and BRISK is performed on three benchmark datasets: the dataset of Mikolajczyk, the INRIA Holidays and the UKbench. Experimental results show that our proposed COGE descriptor significantly outperforms existing schemes.