Colour-appearance modeling using feedforward networks with Bayesian regularization method - Part I: Forward model

In this article, a method of predicting colour appearance (from colorimetri c attributes to colour-appearance attributes, i.e., forward model) rising a n artificial neural network is presented. The neural network model develope d is a multilayer feedforward neural network model for predicting colons ap pearance (FNNCAM for short). The model was trained by LUTCHI colour-appeara nce datasets. The Levenberg-Marquardt algorithm is incorporated into the ba ck-propagation procedure to accelerate the training of FNNCAM and the Bayes ian regularization method is applied to the training of neural networks to improve generalization. The results of FNNCAM obtained are quite promising. (C) 2000 John Wiley & Sons, Inc.