Abstract
Color images often must be color balanced to remove unwanted color casts. We extend previous work on using a neural network for illumination, or white-point, estimation from the case of calibrated images to that of uncalibrated images of unknown origin. The results show that the chromaticity of the ambient illumination can be estimated with an average CIE Lab error of 5ΔE. Comparisons are made to the grayworld and white patch methods.
Original language | English (US) |
---|---|
Pages | 97-100 |
Number of pages | 4 |
State | Published - 1999 |
Externally published | Yes |
Event | Final Program and Proceedings of the 7th IS and T/SID Color Imaging Conference: Color Science, Systems and Applications - Scottsdale, AZ, United States Duration: Nov 16 1999 → Nov 19 1999 |
Other
Other | Final Program and Proceedings of the 7th IS and T/SID Color Imaging Conference: Color Science, Systems and Applications |
---|---|
Country/Territory | United States |
City | Scottsdale, AZ |
Period | 11/16/99 → 11/19/99 |
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition