Abstract
A gsometric-vision approach to color constancy and illuminant estimation is presented in this paper. We show a general framework, based on ideas from the generalized probabilistic Hough translorm, to estimate the illuminant and reflectance ot natural images. Each image pixel votes lor possible illuminants and the estimation is based on cumulative votes. The framework is natural for the introduction of physical constraints in the color constancy problem. We show the relationship of this work 1o previous algorithms for color constancy and present examples.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 1210-1215 |
| Number of pages | 6 |
| Journal | IEEE Transactions on Pattern Analysis and Machine Intelligence |
| Volume | 21 |
| Issue number | 11 |
| DOIs | |
| State | Published - 1999 |
| Externally published | Yes |
All Science Journal Classification (ASJC) codes
- Software
- Computer Vision and Pattern Recognition
- Computational Theory and Mathematics
- Artificial Intelligence
- Applied Mathematics
Keywords
- Bilinear models
- Color constancy
- Hough transform
- Illuminant estimation
- Physical constraints
- Physics-based vision