Application research of machine vision in LCD panel flaw detection

摘要

This paper introduced the machine vision technology into the LCD (Liquid Crystal Display) panel flaw inspection system, in order to detect flaws accurately and quickly. There are two major kinds of flaws in LCD panel: white dots and black dots. Image segmentation can be used to inspect flaws, and a general method is applying a threshold to the whole image. But because of illumination unconformity, the acquired image has varied pixel brightness, and some pixels in the border even have a lower brightness than the black dots. So gradient thresholding based on local pixels is adopted, but because the image sensor and the LCD panel both have a array frame, there exists moire fringes in the image. Thus, a novel method of gradient thresholding based on moire fringes is put forward. And noises handling is discussed at end. Experimental results show that the proposed novel method is effective.