Abstract: It is necessary to detect defects in theproduction process of LCD screens for quality improvements Manual detectionbrings a heavy workload and low accuracy Therefore

an efficient and accurateautomatic detection method is urgently needed To this end

this paper proposesa new defect detection framework

which mainly includes screen area extraction

preprocessing

threshold segmentation and defect selection By adaptiveadjustment of parameters

the detection method can adapt to various complexsituations In order to eliminate the influence of illumination changes

thedefect region is segmented by automatic parameter adjustment in the thresholdsegmentation First

the maximum grayscale value of the image is calculated

andthen the fixed parameters and the coefficient of the defect image aredetermined according to the nodefect image

and finally the maximum value whichwas selected as the minimum threshold of the threshold segmentation from thefixed parameters and the product of the maximum grayscale value and thecoefficient In addition

in order to solve the problem that the brightnessdifference of the images captured by lowresolution cameras is too small todetect defects in the saturation condition

selfadaptive adjustment of exposureparameters was used to collect images to process different parts of images withlarge difference in light and shade Experiments show that the method canachieve high performance and efficiency in detecting defects such as points

lines

Mura

saturation