Skip to content

Improved illumination-invariant descriptors for robust colour object recognition

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Original languageEnglish
Title of host publication2002 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '02)
Publisher or commissioning bodyInstitute of Electrical and Electronics Engineers (IEEE)
Publication dateMay 2002
PagesIV-3393 - IV-3396
Number of pages4
VolumeIV
ISBN (Print)0780374029
DOIs
StatePublished

Publication series

Name
ISSN (Print)15206149

Conference

ConferenceIEEE International Conference on Acoustics, Speech, and Signal Processing
CountryUnited States
CityOrlando, Florida
Period13/05/0217/05/02

Abstract

Colour object recognition is heavily influenced by the variation in the scene illumination conditions. This paper proposes a set of illumination-invariant descriptors of image content. The descriptors are based on a moment-based approach to histogram comparison and, in the case of an object imaged under two different lighting conditions, permit a straightforward recovery of the illumination change involved. The efficacy of the descriptors is compared experimentally with a variety of existing techniques, using an established methodology and an existing purpose-built dataset. The evidence suggests that the new descriptors outperform existing techniques in the area of colour object recognition.

Additional information

Rose publication type: Conference contribution Sponsorship: This work was sponsored by EPSRC grant GR/M84183 under the Link project Autoarch. Terms of use: Copyright © 2002 IEEE. Reprinted from IEEE International Conference on Acoustics, Speech, and Signal Processing, 2002 (ICASSP '02). This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Bristol's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to pubs-permissions@ieee.org. By choosing to view this document, you agree to all provisions of the copyright laws protecting it.

Documents

DOI

Event

IEEE International Conference on Acoustics, Speech, and Signal Processing

Abbreviated TitleICASSP
Duration13 May 200217 May 2002
CountryUnited States
CityOrlando, Florida

Event: Conference

View research connections

Related faculties, schools or groups