Share Email Print

Proceedings Paper

Bootstrapping color constancy
Author(s): Brian V. Funt; Vlad C. Cardei
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Bootstrapping provides a novel approach to training a neural network to estimate the chromaticity of the illuminant in a scene given image data alone. For initial training, the network requires feedback about the accuracy of the network's current results. In the case of a network for color constancy, this feedback is the chromaticity of the incident scene illumination. In the past, prefect feedback has been used, but in the bootstrapping method feedback with a considerable degree of random error can be used to train the network instead. In particular, the grayworld algorithm, which only provides modest color constancy performance, is used to train a neural network which in the end performs better than the grayworld algorithm used to train it.

Paper Details

Date Published: 19 May 1999
PDF: 8 pages
Proc. SPIE 3644, Human Vision and Electronic Imaging IV, (19 May 1999); doi: 10.1117/12.348463
Show Author Affiliations
Brian V. Funt, Simon Fraser Univ. (Canada)
Vlad C. Cardei, Simon Fraser Univ. (Canada)

Published in SPIE Proceedings Vol. 3644:
Human Vision and Electronic Imaging IV
Bernice E. Rogowitz; Thrasyvoulos N. Pappas, Editor(s)

© SPIE. Terms of Use
Back to Top