Using illumination invariant descriptors for recognition
- 1 January 1994
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 355-360
- https://doi.org/10.1109/cvpr.1994.323851
Abstract
Color pixel distributions provide a useful cue for object recognition. Recently, for example, a technique called color indexing due to M. Swain and D. Ballard (1991) used color histograms for the efficient recognition of objects from a large database in the presence of changes in scene geometry and occlusion. The effectiveness of this and other approaches that match color distributions, however, depends on the approximate constancy of the scene illumination. In this paper, we develop color histogram descriptors that are invariant to changes in the intensity and spectral distribution of the illumination. We present a set of experiments that demonstrate the effectiveness of these descriptors for object recognition in the presence of changes in illuminant spectral power distribution.<>Keywords
This publication has 5 references indexed in Scilit:
- Color indexingInternational Journal of Computer Vision, 1991
- Evaluation of linear models of surface spectral reflectance with small numbers of parametersJournal of the Optical Society of America A, 1986
- Survey of Model-Based Image Analysis SystemsThe International Journal of Robotics Research, 1982
- Region extraction and shape analysis in aerial photographsComputer Graphics and Image Processing, 1979
- CorrectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1979