CaltechAUTHORS
  A Caltech Library Service

Recognition of planar object classes

Burl, M. C. and Perona, P. (1996) Recognition of planar object classes. In: 1996 IEEE computer society conference on computer vision and pattern recognition: proceedings. IEEE Computer Society , Los Alamitos, CA, pp. 223-230. ISBN 0-8186-7258-7 http://resolver.caltech.edu/CaltechAUTHORS:20120131-084642667

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

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20120131-084642667

Abstract

We present a new framework for recognizing planar object classes, which is based on local feature detectors and a probabilistic model of the spatial arrangement of the features. The allowed object deformations are represented through shape statistics, which are learned from examples. Instances of an object in an image are detected by finding the appropriate features in the correct spatial configuration. The algorithm is robust with respect to partial occlusion, detector false alarms, and missed features. A 94% success rate was achieved for the problem of locating quasi-frontal views of faces in cluttered scenes.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
http://dx.doi.org/10.1109/CVPR.1996.517078DOIUNSPECIFIED
http://www.computer.org/portal/web/csdl/doi/10.1109/CVPR.1996.517078PublisherUNSPECIFIED
Additional Information:© 1996 IEEE. Date of Current Version: 06 August 2002. The authors wish to thank Thomas Leung of Berkeley for providing the feature detection code and test images used in the face localization experiments. This work is supported in part by the Center for Neuromorphic Systems Engineering as a part of the National Science Foundation Engineering Research Center Program; and by the California Trade and Commerce Agency, Office of Strategic Technology. Generous support of the face localization work was provided by INTEL.
Funders:
Funding AgencyGrant Number
Center for Neuromorphic Systems Engineering (CNSE)UNSPECIFIED
California Trade and Commerce Agency, Office of Strategic TechnologyUNSPECIFIED
INTELUNSPECIFIED
Subject Keywords:computer vision, pattern recognition, object recognition, shape statistics, flexible, deformable, planar objects, point configurations, constellations, face localization, handwriting
Other Numbering System:
Other Numbering System NameOther Numbering System ID
INSPEC Accession Number5329273
Record Number:CaltechAUTHORS:20120131-084642667
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20120131-084642667
Official Citation:M.C. Burl, P. Perona, "Recognition of Planar Object Classes," cvpr, pp.223, 1996 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'96), 1996
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:29031
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:09 Feb 2012 00:10
Last Modified:09 Feb 2012 00:10

Repository Staff Only: item control page