A study of neural network-based LCD display characterization

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

Optimizing Optical Film Lamination to Enhance the Luminance of TFT-LCD Displays Using the Taguchi-NNGA Method

Luminance is an essential quality of a TFT-LCD display. Manufacturers have attempted to improve the soft-to-hard lamination stage to enhance the luminance of their TFT-LCD displays. In addition, many customers have complained about the insufficient luminance of the TFT-LCD displays of the case company. While product engineers have kept tuning the control factors in the soft-to-hard lamination stage through the trial and error method, the improvement of the luminance was not good enough. This study aims to assist the product engineers to fine-tune the settings of the control factors using a new method composed of the Taguchi method, a neural network, and a genetic algorithm. The confirmation experiments showed that the proposed method had increased the average luminance of the TFT-LCD displays from 17.03 to 25.15, which was higher than the required luminance value of 25. As a result, the number of complaints on the TFT-LCD displays had been significantly reduced.