Automatic inspection of an LCD light-guide plate based on weighted central moments combined with neural networks

摘要: Liquid crystal displays (LCDs) have become common display devices. Defects of dot patterns on the light-guide plate an LCD can cause visual failure. A critical task in manufacturing is to detect micro-defective avoid This study proposes integration weighted central moments with artificial neural networks (ANNs) for automatic inspection plate, especially patterns. The proposed algorithm first finds adjustable parameters. Then, back-propagation ANN classifies based shape descriptors moments. Finally, inspects using method successfully classify different plate. also compares results classification and Bayes classifier. comparison shows th...