Abstract
The colour constancy as a problem of Bayesian inference is formulated, where one is trying to represent the posterior on possible interpretations on the given image data. The posterior is represented as a set of samples, drawn from the distribution using a Markov chain Monte Carlo method. This approach has the advantage that it unifies the constraints on the problem, and represents possible ambiguities. In turn, a good description of possible ambiguities means that new information, instead of producing contradictions, is easily incorporated by resampling existing samples. The method is demonstrated on the case where surfaces seen in two distinct images are later discovered to be the same.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 300-305 |
| Number of pages | 6 |
| Journal | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
| Volume | 1 |
| State | Published - Jan 1 1999 |
| Externally published | Yes |
| Event | Proceedings of the 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'99) - Fort Collins, CO, USA Duration: Jun 23 1999 → Jun 25 1999 |
Fingerprint
ASJC Scopus subject areas
- Software
- Computer Vision and Pattern Recognition
Cite this
Sampling, resampling and colour constancy. / Forsyth, D. A.
In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 1, 01.01.1999, p. 300-305.Research output: Contribution to journal › Conference article
}
TY - JOUR
T1 - Sampling, resampling and colour constancy
AU - Forsyth, D. A.
PY - 1999/1/1
Y1 - 1999/1/1
N2 - The colour constancy as a problem of Bayesian inference is formulated, where one is trying to represent the posterior on possible interpretations on the given image data. The posterior is represented as a set of samples, drawn from the distribution using a Markov chain Monte Carlo method. This approach has the advantage that it unifies the constraints on the problem, and represents possible ambiguities. In turn, a good description of possible ambiguities means that new information, instead of producing contradictions, is easily incorporated by resampling existing samples. The method is demonstrated on the case where surfaces seen in two distinct images are later discovered to be the same.
AB - The colour constancy as a problem of Bayesian inference is formulated, where one is trying to represent the posterior on possible interpretations on the given image data. The posterior is represented as a set of samples, drawn from the distribution using a Markov chain Monte Carlo method. This approach has the advantage that it unifies the constraints on the problem, and represents possible ambiguities. In turn, a good description of possible ambiguities means that new information, instead of producing contradictions, is easily incorporated by resampling existing samples. The method is demonstrated on the case where surfaces seen in two distinct images are later discovered to be the same.
UR - http://www.scopus.com/inward/record.url?scp=0032678150&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0032678150&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:0032678150
VL - 1
SP - 300
EP - 305
JO - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
JF - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SN - 1063-6919
ER -