A study of neural network-based LCD display characterization

In this paper we study up to what extent neural networks can be used accurately characterize LCD displays. Using a programmable colorimeter have taken extensive measures for DELL Ultrasharp UP2516D define training and testing data sets that are used, in turn, train validate two networks: one of them using tristimulus values, XYZ, as inputs the other color coordinates, xyY . Both same layer structure which has been experimentally determined. The errors from both models, terms ΔE00 difference, analysed colorimetric point view interpreted order understand how learned is their performance comparison with classical models. As will see, average favor proposed models but it not better all cases regions space.