19 May 1999 Bootstrapping color constancy
Author Affiliations +
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.
© (1999) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Brian V. Funt, Vlad C. Cardei, "Bootstrapping color constancy", Proc. SPIE 3644, Human Vision and Electronic Imaging IV, (19 May 1999); doi: 10.1117/12.348463; https://doi.org/10.1117/12.348463
PROCEEDINGS
8 PAGES


SHARE
Back to Top