Mura defect level judgment method and device based on deep learning

Abstract

The invention relates to a Mura defect level judgment method and device based on deep learning. The method comprises the following steps that: setting a Mura defect level tag, and enabling a Mura defect image sample to correspond to the Mura defect level tag one by one according to a preset level; then, taking the Mura defect image sample as an input neuron to enter a network, carrying out training after feature extraction is carried out, and outputting a training result after the training result passes through a classifier, and obtaining a Mura defect image corresponding to the Mura defect level tag; and finally, outputting the Mura defect image test sample through feature extraction after the Mura defect image test sample passes through the classifier, and comparing with the Mura defectimage sample features with a Mura defect level tag to obtain the Mura defect level corresponding to classification. By use of the method, the Mura defect of a panel can be subjected to accurate and detailed judgment and output, the limitation of a traditional algorithm can be successfully evaded, and meanwhile, human cost can be greatly lowered.

Description

technical field [0001] The present invention relates to a method and a device for judging a Mura defect level, in particular to a method and a device for judging a Mura defect level based on deep learning. Background technique [0002] In AOI defect detection, the evaluation of Mura defect level is very important, which directly affects the final LCD panel defect downgrading judgment result. The traditional Mura classification is based on human eye observation or LCD screen grade inspection standards. The process of human eye detection is highly subjective, which is not conducive to strict classification. At the same time, with the extension of working hours, people will also experience fatigue. , leading to a decrease in detection efficiency; using LCD screen level inspection standards to grade can avoid the disadvantages caused by subjective factors and fatigue of the human eye, but the traditional screen level inspection standards are based on some parameters such as semu...

AI Technical Summary

Problems solved by technology

With the development trend of LCD large screen, thinner, and higher resolution, the probability of mura defects will increase greatly, and the environment will become more and more complex, such as repeated texture background, uneven overall brightness and blurred edges of defects, The low contrast makes it difficult for traditional brightness correction and defect segmentation algorithms in image processing to detect mura defects directly

Images