CaltechAUTHORS
  A Caltech Library Service

A Sparse Object Category Model for Efficient Learning and Complete Recognition

Fergus, Rob and Perona, Pietro and Zisserman, Andrew (2006) A Sparse Object Category Model for Efficient Learning and Complete Recognition. In: Toward Category-Level Object Recognition. Lecture Notes in Computer Science. No.4170. Springer , Berlin, Heidelberg, pp. 443-461. ISBN 9783540687948. https://resolver.caltech.edu/CaltechAUTHORS:20190328-144424435

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20190328-144424435

Abstract

We present a “parts and structure” model for object category recognition that can be learnt efficiently and in a weakly-supervised manner: the model is learnt from example images containing category instances, without requiring segmentation from background clutter. The model is a sparse representation of the object, and consists of a star topology configuration of parts modeling the output of a variety of feature detectors. The optimal choice of feature types (whose repertoire includes interest points, curves and regions) is made automatically. In recognition, the model may be applied efficiently in a complete manner, bypassing the need for feature detectors, to give the globally optimal match within a query image. The approach is demonstrated on a wide variety of categories, and delivers both successful classification and localization of the object within the image.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.1007/11957959_23DOIArticle
ORCID:
AuthorORCID
Perona, Pietro0000-0002-7583-5809
Additional Information:© Springer-Verlag Berlin Heidelberg 2006. We are very grateful for suggestions from and discussions with Michael Isard, Dan Huttenlocher and Alex Holub. Financial support was provided by: EC Project CogViSys; EC PASCAL Network of Excellence, IST-2002-506778; UK EPSRC; Caltech CNSE and the NSF.
Funders:
Funding AgencyGrant Number
European Research Council (ERC)CogViSys
EC PASCAL Network of ExcellenceIST-2002-506778
Engineering and Physical Sciences Research Council (EPSRC)UNSPECIFIED
Center for Neuromorphic Systems Engineering, CaltechUNSPECIFIED
NSFUNSPECIFIED
Series Name:Lecture Notes in Computer Science
Issue or Number:4170
Record Number:CaltechAUTHORS:20190328-144424435
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20190328-144424435
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:94255
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:28 Mar 2019 22:54
Last Modified:03 Oct 2019 21:02

Repository Staff Only: item control page