Unlock instant, AI-driven research and patent intelligence for your innovation.

An OLED defect detection method based on empirical mode decomposition and regression model

An empirical mode decomposition and regression model technology, applied in the field of image processing, can solve the problems of poor reliability, low time-consuming efficiency, etc., and achieve the effects of high reliability, improved accuracy, and improved matching performance.

Active Publication Date: 2020-09-25
DONGGUAN UNIV OF TECH
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides an OLED defect detection method based on empirical mode decomposition and regression model in order to overcome the defects of poor reliability and low time-consuming efficiency in OLED manufacturing defect detection in the above-mentioned prior art

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An OLED defect detection method based on empirical mode decomposition and regression model
  • An OLED defect detection method based on empirical mode decomposition and regression model
  • An OLED defect detection method based on empirical mode decomposition and regression model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] Such as figure 1 Shown, a kind of OLED defect detection method based on empirical mode decomposition and regression model, described method comprises the steps:

[0051] S1: Collecting OLED images (such as figure 2 Shown), and carry out intensity signal analysis to OLED image, obtain OLED image intensity signal data;

[0052] S2: Using the empirical mode decomposition method of the autoregressive model to decompose the OLED image intensity signal according to the x and y directions, the line signal is decomposed into x and y directions, wherein the horizontal direction of the OLED image is taken as the x direction, The vertical direction of the OLED image is taken as the y direction, and the intensity signal components of different frequencies in the x and y directions of the OLED image are obtained, and the high frequency and low frequency components in the intensity signal components of different frequencies in the x and y directions are removed to obtain the x and ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an OLED defect detection method based on empirical mode decomposition and a regression model, and the method comprises the following steps: collecting an OLED image, and carrying out the intensity signal analysis of the OLED image; carrying out line signal decomposition on the OLED image intensity signal according to the x direction and the y direction by adopting an empirical mode decomposition method of an autoregression model, and calculating the side lengths of OLED sub-images in the x direction and the y direction in the OLED image according to the obtained frequency spectrum data; the vertex of the upper left corner of the OLED image serves as an original point, and the side length of the OLED sub-image in the x direction and the y direction is used for defining a cutting grid of the OLED image; cutting the OLED image to obtain a rectangular OLED light-emitting image array; calculating a position offset value of an OLED element in the rectangular OLED light-emitting image array, and adjusting the OLED sub-image to be aligned with the cutting grid according to the position offset value; and selecting an OLED sub-image template, and comparing the OLED sub-image template with the OLED sub-images in the rectangular OLED light-emitting image array one by one to judge whether the OLED has defects or not. The method is high in accuracy and detection efficiency.

Description

technical field [0001] The invention relates to the field of image processing, and more specifically, to an OLED defect detection method based on empirical mode decomposition and regression model. Background technique [0002] OLED (Organic Light Emitting Diode) displays have been used in large-screen TVs, computer monitors, mobile phone screens, etc. The defect detection of OLED (Organic Light Emitting Diode) plays an important role in the quality control of OLED panel manufacturing. There may be defects including chips and cracks in the display pixels, which not only affect the display performance, but also reduce the service life of the product. Therefore, defect detection at the manufacturing stage is very important so that defective circuits can be discarded before forming a finished product. Visual inspection using human eyes may be accurate, but it is very time-consuming and dependent on manpower, and due to defects in human vision and subjective effects caused by h...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06T7/11G06T7/12
Inventor 叶国良叶俊良郭建文罗阳梁经伦张兵
Owner DONGGUAN UNIV OF TECH