# US 2023/0419466 A1 · Method and apparatus for identifying defect grade of bad picture, and storage medium

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

- Number: US 2023/0419466 A1
- Document ID: US20230419466A1
- Status: Published application
- Kind: A1
- Application number: 18/038,197
- Filed: 2020-11-26
- Published: 2023-12-28
- Earliest claimed: 2020-11-26
- Assignees: Boe Technology Group Co., Ltd.
- Applicants: BOE Technology Group Co., Ltd.
- Inventors: Quanguo ZHOU; Kaiqin XU; Jiahong ZOU; Guolin ZHANG; Xun HUANG; Qing ZHANG; Lijia ZHOU; Zhidong WANG; Hongxiang SHEN; Hao TANG; Jiuyang CHENG
- Web page: https://patentgrep.com/patent/US20230419466A1

## CPC

- G06T 7/0002: {Inspection of images, e.g. flaw detection}
- G06T 7/0004: {Industrial image inspection}
- G01N 21/88: Investigating the presence of flaws or contamination
- G06T 3/40: Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30121: CRT, LCD or plasma display
- G06T 2207/30168: Image quality inspection
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)

## Abstract

Provided are a method and apparatus for identifying the defect grade of a bad picture, and a storage medium. The method includes: determining the defect size of a defect from a bad picture; according to a product model corresponding to the bad picture, determining the design size of a pattern corresponding to a component that is adjacent to the position of the defect; determining the defect grade of the defect according to the defect type of the defect and a magnitude relationship between the defect size and the design size, wherein the defect grade is the degree to which the defect affects product yield.

## Claims

### Claim 1

A method for identifying a defect grade of a bad picture, comprising:
determining a defect size of a defect from the bad picture;
according to a product model corresponding to the bad picture, determining a design size of a pattern corresponding to a component that is adjacent to a position of the defect; and
determining the defect grade of the defect according to a defect type of the defect and a magnitude relationship between the defect size and the design size, wherein the defect grade is a degree to which the defect affects product yield.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the determining the defect size of the defect from the bad picture, comprises:
determining a maximum length of the defect in a first direction and a second direction as the defect size, wherein the first direction is perpendicular to the second direction.

### Claim 3 (depends on 1)

The method according to claim 1, wherein the determining the defect grade of the defect according to the defect type of the defect and the magnitude relationship between the defect size and the design size, comprises:
determining the defect type of the defect by a neural network model in an automatic defect classification system, and determining a determination condition of the defect grade used for the defect;
obtaining a determination result by comparing a ratio of the defect size to the design size with a set magnification according to the determination condition; and
determining the defect grade according to the determination result.

### Claim 4 (depends on 3)

The method according to claim 3, wherein in a case that the bad picture is a bad picture in a display panel, the defect type comprises a particle defect and a passivation open defect.

### Claim 5 (depends on 4)

The method according to claim 4, wherein the determining the defect type of the defect by the neural network model in the automatic defect classification system, and determining the determination condition of the defect grade used for the defect, comprises:
in a case that the defect type is the particle defect, determining to use a determination condition of the particle defect for the bad picture, wherein a value of the set magnification ranges from 1.3 to 1.7;
in a case that the defect type is the passivation open defect, determining to use a determination condition of the passivation open defect for the bad picture, wherein a value of the set magnification ranges from 0.8 to 1.2.

### Claim 6 (depends on 5)

The method according to claim 5, wherein the determination condition of the particle defect comprises:
in a case that a pattern around the position of the defect is a pattern corresponding to a channel of a thin film transistor, if a ratio of the defect size to a design size of the channel is less than or equal to the set magnification, determining that the defect grade is bad with quality risk; if the ratio of the defect size to the design size of the channel is greater than the set magnification, determining that the defect grade is bad without quality risk; and
in a case that a pattern around the position of the defect is a pattern corresponding to an intersection of gate lines and data lines of the display panel, if the defect is black and a ratio of the defect size to a design size of the intersection is less than or equal to the set magnification, determining that the defect grade is bad with quality risk; if the ratio of the defect size to the design size of the intersection is greater than the set magnification, determining that the defect grade is bad without quality risk.

### Claim 7 (depends on 5)

The method according to claim 5, wherein the determination condition of the passivation open defect comprises:
in a case that a pattern around the position of the defect is a pattern corresponding to data lines in the display panel, if a ratio of the defect size to a design spacing between two adjacent data lines is less than or equal to the set magnification, determining that the defect grade is bad and repairable; and
if a ratio of the defect size to the design spacing between the two adjacent data lines is greater than the set magnification, determining that the defect grade is bad and unrepairable.

### Claim 8 (depends on 1)

The method according to claim 1, wherein after determining the defect grade of the bad picture, the method further comprises:
labeling defects of different defect grades with different labels.

### Claim 9

(canceled)

### Claim 10

An apparatus for identifying a defect grade of a bad picture, comprising:
at least one processor, and
a memory connected with the at least one processor;
wherein the memory stores instructions that are executable by the at least one processor and the at least one processor is configured to execute the instructions stored in the memory to perform:
determining a defect size of a defect from the bad picture;
according to a product model corresponding to the bad picture, determining a design size of a pattern corresponding to a component that is adjacent to a position of the defect; and
determining the defect grade of the defect according to a defect type of the defect and a magnitude relationship between the defect size and the design size, wherein the defect grade is a degree to which the defect affects product yield.

### Claim 11

A readable storage medium, comprising a memory,
the memory being configured for storing instructions that, when executed by a processor, cause an apparatus comprising the readable storage medium to perform:
determining a defect size of a defect from the bad picture;
according to a product model corresponding to the bad picture, determining a design size of a pattern corresponding to a component that is adjacent to a position of the defect; and
determining the defect grade of the defect according to a defect type of the defect and a magnitude relationship between the defect size and the design size, wherein the defect grade is a degree to which the defect affects product yield.

### Claim 12 (depends on 10)

The apparatus according to claim 10, wherein the at least one processor is further configured to execute the instructions stored in the memory to perform:
determining a maximum length of the defect in a first direction and a second direction as the defect size, wherein the first direction is perpendicular to the second direction.

### Claim 13 (depends on 10)

The apparatus according to claim 10, wherein the at least one processor is further configured to execute the instructions stored in the memory to perform:
determining the defect type of the defect by a neural network model in an automatic defect classification system, and determining a determination condition of the defect grade used for the defect;
obtaining a determination result by comparing a ratio of the defect size to the design size with a set magnification according to the determination condition; and
determining the defect grade according to the determination result.

### Claim 14 (depends on 13)

The apparatus according to claim 13, wherein in a cast that the bad picture is a bad picture in a display panel, the defect type includes a particle defect and a passivation open defect.

### Claim 15 (depends on 14)

The apparatus according to claim 14, wherein the at least one processor is further configured to execute the instructions stored in the memory to perform:
in a case that the defect type is the particle defect, determining to use a determination condition of the particle defect for the bad picture, wherein a value of the set magnification ranges from 1.3 to 1.7;
in a case that the defect type is the passivation open defect, determining to use a determination condition of the passivation open defect for the bad picture, wherein a value of the set magnification ranges from 0.8 to 1.2.

### Claim 16 (depends on 15)

The apparatus according to claim 15, wherein the determination condition of the particle defect includes:
in a case that a pattern around the position of the defect is a pattern corresponding to a channel of a thin film transistor, if a ratio of the defect size to a design size of the channel is less than or equal to the set magnification, determining that the defect grade is bad with quality risk; if the ratio of the defect size to the design size of the channel is greater than the set magnification, determining that the defect grade is bad without quality risk; and
in a case that a pattern around the position of the defect is a pattern corresponding to an intersection of gate lines and data lines of the display panel, if the defect is black and a ratio of the defect size to a design size of the intersection is less than or equal to the set magnification, determining that the defect grade is bad with quality risk; if the ratio of the defect size to the design size of the intersection is greater than the set magnification, determining that the defect grade is bad without quality risk.

### Claim 17 (depends on 15)

The apparatus according to claim 15, wherein the determination condition of the PVX Open defect includes:
in a case that a pattern around the position of the defect is a pattern corresponding to data lines in the display panel, if a ratio of the defect size to a design spacing between two adjacent data lines is less than or equal to the set magnification, determining that the defect grade is bad and repairable; and
if a ratio of the defect size to the design spacing between the two adjacent data lines is greater than the set magnification, determining that the defect grade is bad and unrepairable.

### Claim 18 (depends on 10)

The apparatus according to claim 10, wherein the at least one processor is further configured to execute the instructions stored in the memory to perform:
labeling defects of different defect grades with different labels.

### Claim 19 (depends on 11)

The readable storage medium according to claim 11, wherein the memory is configured for storing the instructions that, when executed by the processor, cause the apparatus comprising the readable storage medium to perform:
determining a maximum length of the defect in a first direction and a second direction as the defect size, wherein the first direction is perpendicular to the second direction

### Claim 20 (depends on 11)

The readable storage medium according to claim 11, wherein the memory is configured for storing the instructions that, when executed by the processor, cause the apparatus comprising the readable storage medium to perform:
determining the defect type of the defect by a neural network model in an automatic defect classification system, and determining a determination condition of the defect grade used for the defect;
obtaining a determination result by comparing a ratio of the defect size to the design size with a set magnification according to the determination condition; and
determining the defect grade according to the determination result.

### Claim 21 (depends on 20)

The readable storage medium according to claim 20, wherein in a case that the bad picture is a bad picture in a display panel, the defect type comprises a particle defect and a passivation open defect.
