A Fuzzy Logic Inference System for Display Characterization.

We present in this paper the application of a fuzzy logic inference system to characterize liquid-crystal displays. We use the so-called fuzzy modelling and identification toolbox (FMID, Mathworks) to build a fuzzy logic inference system from a set of input and output data. The advantage of building a model like this, aside from its good performance, relies on its interpretability. Once trained, we obtain a physical interpretation of the model. We use training and testing datasets relating device dependent RGB data with device independent XYZ or xyY coordinates, measured with a colorimeter. We study different configurations for the model and compare them with three state-of-the-art methods in terms of Δ E 00 visual error. This study is restricted to a single display and therefore we also point out what features of the learned model we think are more display dependent and might possibly change for a different display.