Share Email Print
cover

Proceedings Paper

Decoupling sparse coding of SIFT descriptors for large-scale visual recognition
Author(s): Zhengping Ji; James Theiler; Rick Chartrand; Garrett Kenyon; Steven P. Brumby
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

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.

Paper Details

Date Published: 29 May 2013
PDF: 10 pages
Proc. SPIE 8750, Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering XI, 87500K (29 May 2013); doi: 10.1117/12.2018204
Show Author Affiliations
Zhengping Ji, Los Alamos National Lab. (United States)
James Theiler, Los Alamos National Lab. (United States)
Rick Chartrand, Los Alamos National Lab. (United States)
Garrett Kenyon, Los Alamos National Lab. (United States)
Steven P. Brumby, Los Alamos National Lab. (United States)


Published in SPIE Proceedings Vol. 8750:
Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering XI
Harold H. Szu, Editor(s)

© SPIE. Terms of Use
Back to Top