An Image Enhancement Technique in Inspecting Visual Defects of Polarizers in TFT-LCD Industry

This study develops an image-processing filter to enhance the visual defects such as particles, stains, and uneven intensity on polarizers in TFT-LCD industry. Each pixel in the subimage of a polarizer is initially processed to calculate its standard deviation (SD) of gray level, which is sampled by its neighbors within a window. The gray level of each pixel is re-scaled by the maximal and minimal SD values on entire subimage to determine its new gray level. Real polarizers with visual defects are tested in this study. Experimental results show that the proposed filter achieves better performance than conventional image enhancement filters do. Moreover, the proposed image enhancement scheme provides more information for potential defect detection and classification alternatives. The proposed filter is simple, straightforward, and requiring no high-resolution image. Therefore, it is practically suitable for large-polarizer manufacturers to increase inspection speed.