Learning a Color Algorithm from Examples

Abstract

A lightness algorithm that separates surface reflectance from illumination in a Mondrian world is synthesized automatically from a set of examples, pairs of input (image irradiance) and desired output (surface reflectance). The algorithm, which re(cid:173) sembles a new lightness algorithm recently proposed by Land, is approximately equiva(cid:173) lent to filtering the image through a center-surround receptive field in individual chro(cid:173) matic channels. The synthesizing technique, optimal linear estimation, requires only one assumption, that the operator that transforms input into output is linear. This assumption is true for a certain class of early vision algorithms that may therefore be synthesized in a similar way from examples. Other methods of synthesizing algorithms from examples, or "learning", such as backpropagation, do not yield a significantly dif(cid:173) ferent or better lightness algorithm in the Mondrian world. The linear estimation and backpropagation techniques both produce simultaneous brightness contrast effects.

Cite

Text

Poggio and Hurlbert. "Learning a Color Algorithm from Examples." Neural Information Processing Systems, 1987.

Markdown

[Poggio and Hurlbert. "Learning a Color Algorithm from Examples." Neural Information Processing Systems, 1987.](https://mlanthology.org/neurips/1987/poggio1987neurips-learning/)

BibTeX

@inproceedings{poggio1987neurips-learning,
  title     = {{Learning a Color Algorithm from Examples}},
  author    = {Poggio, Tomaso A. and Hurlbert, Anya C.},
  booktitle = {Neural Information Processing Systems},
  year      = {1987},
  pages     = {622-631},
  url       = {https://mlanthology.org/neurips/1987/poggio1987neurips-learning/}
}