CN-121981960-A - Point defect detection method, device and equipment

CN121981960ACN 121981960 ACN121981960 ACN 121981960ACN-121981960-A

Abstract

The application provides a point defect detection method, a device and equipment, and relates to the technical field of defect detection, wherein the method comprises the steps of acquiring a gray-scale image shot by a camera aiming at a display picture; and carrying out preprocessing operation on the gray-scale image to obtain a preprocessed image, wherein the preprocessing operation comprises Laplacian enhancement operation, and determining a defect area of the preprocessed image according to Laplacian characteristics of the preprocessed image and a corresponding characteristic threshold value. The technical scheme provided by the application can detect the real point defects by a visual algorithm without depending on labeling data and model training, shooting a side view image or manual judgment, and can improve the detection efficiency and accuracy of the point defects.

Inventors

WANG NINI
WANG XIAOMAN
GAO XIANG
LIANG JIANHUA
TANG YINGYING
LIU YAOCHENG

Assignees

青岛歌尔视显科技有限公司

Dates

Publication Date: 20260505
Application Date: 20251226

Claims (10)

1. A point defect detection method, characterized by comprising: acquiring a gray-scale image shot by a camera aiming at a display picture; Preprocessing the gray-scale image to obtain a preprocessed image, wherein the preprocessing operation comprises Laplace enhancement operation; And determining a defect area of the preprocessed image according to the Laplacian characteristic of the preprocessed image and the corresponding characteristic threshold value.
2. The method of claim 1, wherein the noise filtering is performed using Gaussian filtering and the image enhancement is performed using Laplace enhancement, and wherein the preprocessing operation further comprises a filtering operation performed prior to the Laplace enhancement operation.
3. The method of claim 1, wherein the preprocessing operation further comprises a gray scale normalization operation performed after the Laplace enhancement operation, wherein the Laplace characteristics comprise peak, mean and high response duty cycle; the determining the defect area of the preprocessed image according to the Laplacian feature of the preprocessed image and the corresponding feature threshold value comprises the following steps: determining a connected region formed by a target pixel in the preprocessed image as a defect candidate region, wherein the Laplace value of the target pixel is larger than a target Laplace threshold value; And determining a defect area from the defect candidate areas, wherein the peak value of the defect area is larger than a first threshold value, the mean value of the defect area is smaller than a second threshold value and the high response duty ratio of the defect area is larger than a third threshold value.
4. The method of claim 1, wherein after the acquiring the grayscale image captured by the camera for the different grayscales of the display, before the preprocessing operation is performed on the grayscale image, the method further comprises: and carrying out dynamic threshold segmentation on the gray-scale image, and removing a background area in the gray-scale image.
5. The method according to claim 1, wherein the method further comprises: Determining the minimum circumscribed rectangle of point defects in each defect area; determining a point defect area from each of the defect areas according to the aspect ratio of each of the minimum bounding rectangles and a point defect threshold; And determining the position information of the point defect area.
6. The method of claim 1, wherein prior to capturing images captured by the camera for different gray levels of the display, the method further comprises: the surface of the display screen is cleaned by adopting a mode of combining unidirectional wet wiping and dry wiping; crimping to lighten the display screen; And adjusting the position of the display screen to enable the light-emitting area of the display screen to be positioned in the central area of the visual field of the camera.
7. The method according to any one of claims 1-6, further comprising: Generating a point defect information recording table based on the defect area, wherein the point defect information recorded in the point defect information recording table includes at least one of a gray value of the point defect, position information of the point defect, and the number of the point defect.
8. A point defect detecting device, characterized by comprising: the acquisition module acquires a gray-scale image shot by the camera aiming at the display picture; the processing module is used for carrying out preprocessing operation on the gray-scale image to obtain a preprocessed image, wherein the preprocessing operation comprises Laplace enhancement operation; And the determining module is used for determining a defect area of the preprocessed image according to the Laplace characteristic of the preprocessed image and the corresponding characteristic threshold value.
9. A point defect detection apparatus comprising a memory for storing a computer program and a processor for executing the method according to any one of claims 1-7 when the computer program is invoked.
10. A computer program product, characterized in that the computer program product, when run on a point defect detection apparatus, causes the point defect detection apparatus to perform the method according to any of claims 1-7.

Description

Point defect detection method, device and equipment Technical Field The present application relates to the field of defect detection technologies, and in particular, to a method and an apparatus for detecting a point defect, and an electronic device. Background The point defect is a common defect in the manufacturing process of an Organic light-emitting diode display screen (Organic LIGHT EMITTING DISPLAY, OLED), and the main reasons for the generation of the point defect include uneven distribution of Organic matters on a light-emitting layer, unreasonable structural design of an electrode and physical shielding caused by impurity coverage. The point defect in the OLED display screen is represented by a tiny area of which the brightness, color or luminous state is inconsistent with that of a normal display area, and the abnormal state of the area is usually fixed and cannot disappear along with the change of the content of a display picture. The presence of spot defects can affect the display effect, and long-term use may induce more serious performance problems and even cause defect diffusion, so that defect detection is required for the OLED display screen in order to ensure the product quality. However, the existing point defect detection method generally depends on personnel experience, has low efficiency and cannot meet the real-time requirement of a production line. Disclosure of Invention In view of the above, the embodiments of the present application provide a method, an apparatus and a device for detecting a point defect, which are used for improving the detection efficiency of the point defect. In order to achieve the above object, in a first aspect, an embodiment of the present application provides a method for detecting a point defect, including: acquiring a gray-scale image shot by a camera aiming at a display picture; Preprocessing the gray-scale image to obtain a preprocessed image, wherein the preprocessing operation comprises Laplace enhancement operation; And determining a defect area of the preprocessed image according to the Laplacian characteristic of the preprocessed image and the corresponding characteristic threshold value. In a possible implementation manner of the first aspect, the noise filtering is performed by using gaussian filtering, the image enhancement is performed by using laplace enhancement, and the preprocessing operation further includes a filtering operation performed before the laplace enhancement operation. In one possible implementation of the first aspect, the preprocessing operation further includes a gray scale normalization operation performed after the laplace enhancement operation, the laplace features including peak, mean, and high response duty cycle; the determining the defect area of the preprocessed image according to the Laplace characteristic comprises the following steps: determining a connected region formed by a target pixel in the preprocessed image as a defect candidate region, wherein the Laplace value of the target pixel is larger than a target Laplace threshold value; And determining a defect area from the defect candidate areas, wherein the peak value of the defect area is larger than a first threshold value, the mean value of the defect area is smaller than a second threshold value and the high response duty ratio of the defect area is larger than a third threshold value. In a possible implementation manner of the first aspect, after the acquiring the gray-scale image captured by the camera for different gray scales of the display screen, before performing the preprocessing operation on the gray-scale image, the method further includes: and carrying out dynamic threshold segmentation on the gray-scale image, and removing a background area in the gray-scale image. In a possible implementation manner of the first aspect, the method further includes: Determining the minimum circumscribed rectangle of point defects in each defect area; determining a point defect area from each of the defect areas according to the aspect ratio of each of the minimum bounding rectangles and a point defect threshold; And determining the position information of the point defect area. In a possible implementation manner of the first aspect, before acquiring the images captured by the camera for different gray scales of the display screen, the method further includes: the surface of the display screen is cleaned by adopting a mode of combining unidirectional wet wiping and dry wiping; crimping to lighten the display screen; And adjusting the position of the display screen to enable the light-emitting area of the display screen to be positioned in the central area of the visual field of the camera. In a possible implementation manner of the first aspect, the method further includes: Generating a point defect information recording table based on the defect area, wherein the point defect information recorded in the point defect information recording table includes at le