# US 12,223,638 B2 · Display defect detection system and detection method thereof

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,223,638 B2
- Document ID: US12223638B2
- Status: Granted
- Kind: B2
- Application number: 17/891,714
- Filed: 2022-08-19
- Published: 2023-06-15
- Granted: 2025-02-11
- Earliest claimed: 2021-12-14
- Assignees: LG Display Co., Ltd.
- Applicants: LG Display Co., Ltd.
- Inventors: Ki Hyun Kim; Jong Ju Hong
- Web page: https://patentgrep.com/patent/US12223638B2

## CPC

- G06T 7/0004: {Industrial image inspection}
- G06T 7/0008: {checking presence/absence}
- G06T 5/70: Denoising; Smoothing
- G06T 7/13: Edge detection
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06V 10/242: {by image rotation, e.g. by 90 degrees}
- G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI]
- G06V 10/50: by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
- G06T 2207/20182: Noise reduction or smoothing in the temporal domain; Spatio-temporal filtering
- G06T 2207/30121: CRT, LCD or plasma display
- G06V 2201/07: Target detection
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A display defect detection system and a detection method thereof are disclosed. A display defect detection system includes a preprocessing circuit receiving a capture image of a test pattern, displayed by a display panel, as a panel image including diagonal Mura and preprocessing the panel image to output a preprocessing image and a Mura detection circuit calculating a final feature value of the diagonal Mura by multiplying a first feature value, in which a luminance difference of the diagonal Mura is reflected, by a second feature value in which a shape ratio of the diagonal Mura is reflected, on the basis of an edge map of the preprocessing image, and detecting a display position of the diagonal Mura on the basis of the final feature value of the diagonal Mura.

## Claims

### Claim 1

A display defect detection system, comprising:
a preprocessing circuit receiving a capture image of a test pattern, displayed by a display panel, as a panel image including diagonal Mura and preprocessing the panel image to output a preprocessing image; and
a Mura detection circuit calculating a final feature value of the diagonal Mura by multiplying a first feature value, in which a luminance difference of the diagonal Mura is reflected, by a second feature value in which a shape ratio of the diagonal Mura is reflected, on the basis of an edge map of the preprocessing image, and detecting a display position of the diagonal Mura on the basis of the final feature value of the diagonal Mura.

### Claim 2 (depends on 1)

The display defect detection system of claim 1, wherein a preprocessing process performed by the preprocessing circuit comprises:
a process of cropping the panel image to extract a region of interest ROI including the diagonal Mura and changing a size of the ROI to a predetermined size;
a process of normalizing a color sense or brightness of the ROI; and
a process of removing a noise component, hindering detection of the diagonal Mura, from the normalized ROI.

### Claim 3 (depends on 1)

The display defect detection system of claim 1, wherein the Mura detection circuit comprises:
an edge detector generating an edge map image including edge information about the preprocessing image;
a block calculator dividing the edge map image by block units and calculating a block edge feature value corresponding to each of edge map block images;
a Mura candidate selector selecting an edge map block image, where the block edge feature value is greater than or equal to a reference value, as a Mura candidate image from among the edge map block images;
a shape ratio calculator projecting diagonal Mura included in the Mura candidate image in an x-axis direction and a y-axis direction with respect to each of a plurality of angles while rotating the Mura candidate image at the plurality of angles and calculating, as a shape ratio feature value of the diagonal Mura, a projection ratio value corresponding to an angle where a projection ratio value between the x-axis direction and the y-axis direction is largest; and
a final feature value calculator multiplying a block edge feature value of the Mura candidate image indicating the first feature value by a shape ratio feature value of the diagonal Mura indicating the second feature value to calculate a luminance-shape ratio feature value indicating the final feature value of the diagonal Mura.

### Claim 4 (depends on 3)

The display defect detection system of claim 3, wherein each of the edge map image and the Mura candidate image is a binary image.

### Claim 5 (depends on 3)

The display defect detection system of claim 3, wherein the Mura candidate selector selects an edge map block image, where the block edge feature value is upper 10%, as the Mura candidate image from among the edge map block images and filters out and removes an edge map block image where the block edge feature value is less than upper 10%.

### Claim 6 (depends on 3)

The display defect detection system of claim 3, wherein the projection ratio value between the x-axis direction and the y-axis direction comprises a first ratio value obtained by dividing an x axis-direction projection value by a y axis-direction projection value and a second ratio value obtained by dividing the y axis-direction projection value by the x axis-direction projection value.

### Claim 7 (depends on 6)

The display defect detection system of claim 6, wherein the shape ratio calculator calculates a plurality of first ratio values and a plurality of second ratio values with respect to the plurality of angles and calculates, as a shape ratio feature value of the diagonal Mura, one largest ratio value of the plurality of first ratio values and the plurality of second ratio values.

### Claim 8 (depends on 3)

The display defect detection system of claim 3, wherein the edge detector detects edge features in an x-axis direction and a y-axis direction by using a Sobel filter and weight-averages the edge features to generate the edge map image.

### Claim 9

A display defect detection method, comprising:
receiving a capture image of a test pattern, displayed by a display panel, as a panel image including diagonal Mura and preprocessing the panel image to output a preprocessing image;
calculating a final feature value of the diagonal Mura by multiplying a first feature value, in which a luminance difference of the diagonal Mura is reflected, by a second feature value in which a shape ratio of the diagonal Mura is reflected, on the basis of an edge map of the preprocessing image; and
detecting a display position of the diagonal Mura on the basis of the final feature value of the diagonal Mura.

### Claim 10 (depends on 9)

The display defect detection method of claim 9, wherein the preprocessing the panel image comprises:
cropping the panel image to extract a region of interest ROI including the diagonal Mura and changing a size of the ROI to a predetermined size;
normalizing a color sense or brightness of the ROI; and
removing a noise component, hindering detection of the diagonal Mura, from the normalized ROI.

### Claim 11 (depends on 9)

The display defect detection method of claim 9, wherein the calculating the final feature value of the diagonal Mura comprises:
generating an edge map image including edge information about the preprocessing image;
dividing the edge map image by block units and calculating a block edge feature value corresponding to each of edge map block images;
selecting an edge map block image, where the block edge feature value is greater than or equal to a reference value, as a Mura candidate image from among the edge map block images;
projecting diagonal Mura included in the Mura candidate image in an x-axis direction and a y-axis direction with respect to each of a plurality of angles while rotating the Mura candidate image at the plurality of angles and calculating, as a shape ratio feature value of the diagonal Mura, a projection ratio value corresponding to an angle where a projection ratio value between the x-axis direction and the y-axis direction is largest; and
multiplying a block edge feature value of the Mura candidate image indicating the first feature value by a shape ratio feature value of the diagonal Mura indicating the second feature value to calculate a luminance-shape ratio feature value indicating the final feature value of the diagonal Mura.

### Claim 12 (depends on 11)

The display defect detection method of claim 11, wherein each of the edge map image and the Mura candidate image is a binary image.

### Claim 13 (depends on 11)

The display defect detection method of claim 11, wherein the selecting the Mura candidate image comprises:
selecting an edge map block image, where the block edge feature value is upper 10%, as the Mura candidate image from among the edge map block images; and
filtering out and removing an edge map block image where the block edge feature value is less than upper 10%.

### Claim 14 (depends on 11)

The display defect detection method of claim 11, wherein the projection ratio value between the x-axis direction and the y-axis direction comprises a first ratio value obtained by dividing an x axis-direction projection value by a y axis-direction projection value and a second ratio value obtained by dividing the y axis-direction projection value by the x axis-direction projection value.

### Claim 15 (depends on 14)

The display defect detection method of claim 14, wherein the calculating the projection ratio value as the shape ratio feature value comprises:
calculating a plurality of first ratio values and a plurality of second ratio values with respect to the plurality of angles; and
calculating, as a shape ratio feature value of the diagonal Mura, one largest ratio value of the plurality of first ratio values and the plurality of second ratio values.

### Claim 16 (depends on 11)

The display defect detection method of claim 11, wherein the generating the edge map image comprises: detecting edge features in an x-axis direction and a y-axis direction by using a Sobel filter and weight-averaging the edge features to generate the edge map image.