Coordinate transformation of object colors using neural networks

Abstract

Coordinate transformation between the Munsell and CIE-XYZ color systems is often needed in measuring and displaying object colors. No equation has been defined that specifies a direct transformation between two color spaces, but a table of data provides numerical correspondence between the two systems. So far, the transformation has been done by the complicated method of three-dimensional interpolation to this table of data. This paper proposes a new method of transformation using neural networks. A multilayer network is considered as a nonlinear transformer that adaptively learns a relationship between two color spaces. The complex mapping can then be executed rapidly by linking simple nonlinear units in parallel and in multilayers. The table of data is used for network learning by the back propagation method and for testing the performance. The input and output units correspond to three color coordinates in two color systems. A 3-10-10-10-3 type network with three hidden layers of 10 units is obtained as the most suitable one. The accuracy of transformation is examined on computer experiments. In our transformation method the database is not necessary, and the table of a large amount of data is replaced with about 300 weighting coefficients to link units in the network.