1 July 2009 Visual codebook construction for class-specific recognition
Author Affiliations +
Abstract
Creating a visual codebook is an important problem in object recognition. Using a compact visual codebook can boost computational efficiency and reduce memory cost. A simple and effective method is proposed for visual feature codebook construction. On the basis of a feedforward hierarchical model, a robust local descriptor is proposed and an a priori statistical scheme is applied to the class-specific feature-learning stage. The experiments show that the proposed approach achieves reliable performance with shorter codebook length, and incremental learning can be easily enabled.
© (2009) Society of Photo-Optical Instrumentation Engineers (SPIE)
Jun Gao, Jun Gao, Nong Sang, Nong Sang, Changxin Gao, Changxin Gao, Qiling Tang, Qiling Tang, Sang Jun, Sang Jun, } "Visual codebook construction for class-specific recognition," Optical Engineering 48(7), 077201 (1 July 2009). https://doi.org/10.1117/1.3160333 . Submission:
JOURNAL ARTICLE
5 PAGES


SHARE
Back to Top