Translator Disclaimer
8 September 2011 Discriminative region extraction and feature selection based on the combination of SURF and saliency
Author Affiliations +
The objective of this paper is to provide a possible optimization on salient region algorithm, which is extensively used in recognizing and learning object categories. Salient region algorithm owns the superiority of intra-class tolerance, global score of features and automatically prominent scale selection under certain range. However, the major limitation behaves on performance, and that is what we attempt to improve. By reducing the number of pixels involved in saliency calculation, it can be accelerated. We use interest points detected by fast-Hessian, the detector of SURF, as the candidate feature for saliency operation, rather than the whole set in image. This implementation is thereby called Saliency based Optimization over SURF (SOSU for short). Experiment shows that bringing in of such a fast detector significantly speeds up the algorithm. Meanwhile, Robustness of intra-class diversity ensures object recognition accuracy.
© (2011) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Li Deng, Chunhong Wang, and Changhui Rao "Discriminative region extraction and feature selection based on the combination of SURF and saliency", Proc. SPIE 8193, International Symposium on Photoelectronic Detection and Imaging 2011: Advances in Infrared Imaging and Applications, 819310 (8 September 2011);


Back to Top