Method for light source discrimination and facial pattern detection from negative color lm
- Demas Sanger, Hideaki Haneishi, Yoichi Miyake
- Journal of Imaging Science and Technologie,
The application of a multi-layer perceptron for color and gray level correction in the eld of photoonishing is presented. It is shown, that a neural network 1] 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 rst time, to process this large database in a reasonable time.