Decoupling sparse coding of SIFT descriptors for large-scale visual recognition
Zhengping Ji, James P. Theiler, Rick Chartrand, Garrett T. Kenyon, Steven P. Brumby · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2013
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.