Decoupling sparse coding of SIFT descriptors for large-scale visual recognition

Zhengping Ji; James Theiler; Rick Chartrand; Garrett Kenyon; Steven P. Brumby

doi:10.1117/12.2018204

29 May 2013 Decoupling sparse coding of SIFT descriptors for large-scale visual recognition

Zhengping Ji, James Theiler, Rick Chartrand, Garrett Kenyon, Steven P. Brumby

Proceedings Volume 8750, Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering XI; 87500K (2013) https://doi.org/10.1117/12.2018204
Event: SPIE Defense, Security, and Sensing, 2013, Baltimore, Maryland, United States

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.

Citation Download Citation

Zhengping Ji, James Theiler, Rick Chartrand, Garrett Kenyon, and 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); https://doi.org/10.1117/12.2018204

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available