Color Notation Conversion between the Munsell and CIE Color Systems Using Neural Networks

Abstract

This paper describes a new method for converting color notation between the Munsell and CIE color systems by means of neural networks. A multilayer feedforward network is regarded as a nonlinear transformer and is trained to learn the mapping between the two color spaces using the Back-Propagation learning rule. The mapping is then represented in a simple network architecture in which nonlinear units are linked in parallel and in layers. Using Nickerson's tables for computer simulation of the training and testing phases, an effective network structure and training strategy is determined based on experiments under different conditions. The conversion accuracy is demonstrated in both directions, Munsell-to-CIE and CIE-to-Munsell. The Munsell colors are displayed on a calibrated color monitor and their accuracy is confirmed visually.