Los Alamos National Laboratory
Phone| Search
T-5 HomeResearchPublications › ji-2013-sift
› Contact › People › Research
› Projects › Highlights › Publications
› Jobs › Visitor Info

Cite Details

Zhengping Ji, James Theiler, Rick Chartrand, Garrett Kenyon and Steven P. Brumby, "SIFT-based sparse coding for large-scale visual recognition", in SPIE Defense, Security, and Sensing, 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.

BibTeX Entry

author = {Zhengping Ji and James Theiler and Rick Chartrand and Garrett Kenyon and Steven P. Brumby},
title = {SIFT-based sparse coding for large-scale visual recognition},
year = {2013},
urlpdf = {http://math.lanl.gov/Research/Publications/Docs/ji-2013-sift.pdf},
booktitle = {SPIE Defense, Security, and Sensing}