A mura detection method based on adaptive selection of independent components

Abstract

The invention provides a Mura detection method based on adaptive selection of independent components. The method includes the following steps: combining N input images into a mixing matrix; performing ICA transformation on the mixing matrix to obtain N independent components; selecting one of the N input images as a comparison image, and calculating each The SSIM value between an independent component and the comparison image; setting the background range of each independent component and counting the number of brightness extreme points in each independent component; calculating the comparison of each independent component according to the SSIM value and the number of each brightness extreme point value, and select the independent component with the largest comparison value as the target independent component; perform ICA inverse transformation on the target independent component to obtain a defect-enhanced image, and select the defect threshold to perform defect segmentation on the defect-enhanced image, which can replace the adaptive selection of the human eye Target independent components to meet the needs of production automation.

Description

Technical field [0001] The present invention relates to the field of display technology, and in particular to a Mura detection method based on independent component adaptive selection. Background technique [0002] With the development of display technology, flat display devices such as Liquid Crystal Display (LCD) and Organic Light Emitting Display (OLED) have high image quality, power saving, thin body and wide application range. It has been widely used in various consumer electronic products such as mobile phones, TVs, personal digital assistants, digital cameras, notebook computers, desktop computers, etc., and has become the mainstream of display devices. [0003] With the development of technology and the needs of people's material life, the size of cash flat-panel displays has become larger and larger, the display resolution has become higher and higher, and the requirements for production processes have become more and more stringent. At present, mura is often generated du...

AI Technical Summary

Problems solved by technology

[0004] The existence of Mura will not affect the use function of the display panel, but it will reduce the user's viewing comfort, so Mura restricts the development of LCD displays and OLED displays

Due to the complex background of the displayed image, the mura area has low contrast and no obvious boundary relative to the background, so it is difficult to quantify the mura area

In the prior art, the method of Independent Component Correlation Algorithm (ICA) is often used to enhance the contrast between the Mura area and the background area. Generally, the process of independent component analysis includes: forming a mixing matrix from multiple input images and performing a process on the mixing matrix. ICA transformation, to obtain multiple independent components, and select the independent component closest to the original image as the target independent component for ICA inverse transformation, to obtain a defect (Mura) enhanced image, in which the process of selecting the independent component closest to the original image requires Judging and selecting by human eyes, it is not convenient to actively and adaptively select the closest independent component, which cannot meet the needs of production automation

Images