We show that a color algorithm capable of separating illumination from reflectance in a Mondrian world can be learned from a set of examples. The learned algorithm is equivalent to filtering the image data---in which reflectance and illumination are mixed---through a center-surround receptive field in individual chromatic channels. The operation resembles the "retinex" algorithm recently proposed by Edwin Land. This result is a specific instance of our earlier results that a standard regularization algorithm can be learned from examples. It illustrates that the natural constraints needed to solve a problemsin inverse optics can be extracted directly from a sufficient set of input data and the corresponding solutions. The learning procedure has been implemented as a parallel algorithm on the Connection Machine System.
| Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/5601 |
| Date | 01 June 1987 |
| Creators | Hurlbert, Anya, Poggio, Tomaso |
| Source Sets | M.I.T. Theses and Dissertation |
| Language | en_US |
| Detected Language | English |
| Format | 30 p., 4549310 bytes, 1641242 bytes, application/postscript, application/pdf |
| Relation | AIM-909 |
Page generated in 0.0116 seconds