29 May 2013 Decoupling sparse coding of SIFT descriptors for large-scale visual recognition
Author Affiliations +
In recent years, sparse coding has drawn considerable research attention in developing feature representations for visual recognition problems. In this paper, we devise sparse coding algorithms to learn a dictionary of basis functions from Scale- Invariant Feature Transform (SIFT) descriptors extracted from images. The learned dictionary is used to code SIFT-based inputs for the feature representation that is further pooled via spatial pyramid matching kernels and fed into a Support Vector Machine (SVM) for object classification on the large-scale ImageNet dataset. We investigate the advantage of SIFT-based sparse coding approach by combining different dictionary learning and sparse representation algorithms. Our results also include favorable performance on different subsets of the ImageNet database.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Zhengping Ji, James Theiler, Rick Chartrand, Garrett Kenyon, Steven P. Brumby, "Decoupling sparse coding of SIFT descriptors for large-scale visual recognition", Proc. SPIE 8750, Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering XI, 87500K (29 May 2013); doi: 10.1117/12.2018204; https://doi.org/10.1117/12.2018204

Back to Top