MUSIC perceptron
3 June 1996
MUSIC perceptron, vision model published 1996-06-03. Notable for: historical significance.
Connections
No links yet. This entry came from a dataset and has not been written up.
Abstract
The application of a multilayer perceptron for color and gray level correction in the field of photofinishing is presented. It is shown, that a neural network can improve the overall performance of a state of the art photo printer. The improved correction ability will reduce the number of unsalable pictures and thus lowers the production costs for the photo laboratory. The training experiments were carried out on a database of 30,000 photos using the MUSIC parallel supercomputer. The MUSIC system made it possible, for the first time, to process this large database in a reasonable time.
Sources: Epoch AI. This entry was generated from a dataset and has not been edited by hand.