Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published August 2010 | Published
Journal Article Open

Learning Object Categories From Internet Image Searches

Abstract

In this paper, we describe a simple approach to learning models of visual object categories from images gathered from Internet image search engines. The images for a given keyword are typically highly variable, with a large fraction being unrelated to the query term, and thus pose a challenging environment from which to learn. By training our models directly from Internet images, we remove the need to laboriously compile training data sets, required by most other recognition approaches-this opens up the possibility of learning object category models "on-the-fly." We describe two simple approaches, derived from the probabilistic latent semantic analysis (pLSA) technique for text document analysis, that can be used to automatically learn object models from these data. We show two applications of the learned model: first, to rerank the images returned by the search engine, thus improving the quality of the search engine; and second, to recognize objects in other image data sets.

Additional Information

© 2010 IEEE. Manuscript received April 7, 2009; revised September 23, 2009; accepted March 22, 2010. Date of publication June 10, 2010; date of current version July 21, 2010. This work was supported by the Caltech Center for Neuromorphic Systems Engineering (CNSE), the U.K. Engineering and Physical Sciences Research Council (EPSRC), European Union NOE PASCAL, the European Research Council (ERC) under Grant VisRec, and the U.S. Office of Naval Research (ONR) Multidisciplinary University Research Initiative (MURI) under Grants N00014-06-1-0734 and N00014-07-1-0182. The authors would like to thank David Forsyth.

Attached Files

Published - Fergus2010p11824P_Ieee.pdf

Files

Fergus2010p11824P_Ieee.pdf
Files (3.0 MB)
Name Size Download all
md5:fbdfd3b8940151f81053a17c95ba4c30
3.0 MB Preview Download

Additional details

Created:
August 22, 2023
Modified:
October 20, 2023