Automatic inspection of salt-and-pepper defects in OLED panels using image processing and control chart techniques

Jueun Kwak, Ki Bum Lee, Jaeyeon Jang, Kyong Soo Chang, Chang Ouk Kim

Research output: Contribution to journalArticle

Abstract

In the manufacture of flat display panels, salt-and-pepper defects are caused by a malfunction in the chemical process. The defects are characterized by the dispersion of many black and white pixels in the display panels; these pixels are difficult to detect with conventional automatic fault detection methods that specialize in recognizing certain shapes, such as line or mura defects (stains). This study proposes a simple but high-performance salt-and-pepper defect detection method. First, the background image of the original image is generated using the mean filter in the spatial domain to create a noise image, which is the subtraction of the two images. A binary image is then obtained from the noise image to count the defective pixels, and a statistical control chart that monitors the number of defective pixels identifies the panel defects. Two experiments were conducted with images collected from an organic light-emitting diode inspection process, and the proposed method showed excellent performance with respect to classification accuracy and processing time.

Original languageEnglish
Pages (from-to)1047-1055
Number of pages9
JournalJournal of Intelligent Manufacturing
Volume30
Issue number3
DOIs
Publication statusPublished - 2019 Mar 15

Fingerprint

Organic light emitting diodes (OLED)
Image processing
Inspection
Pixels
Salts
Defects
Display devices
Flat panel displays
Binary images
Fault detection
Control charts
Processing
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Industrial and Manufacturing Engineering
  • Artificial Intelligence

Cite this

@article{0ee5b77f499045c89bcd70895fd70af7,
title = "Automatic inspection of salt-and-pepper defects in OLED panels using image processing and control chart techniques",
abstract = "In the manufacture of flat display panels, salt-and-pepper defects are caused by a malfunction in the chemical process. The defects are characterized by the dispersion of many black and white pixels in the display panels; these pixels are difficult to detect with conventional automatic fault detection methods that specialize in recognizing certain shapes, such as line or mura defects (stains). This study proposes a simple but high-performance salt-and-pepper defect detection method. First, the background image of the original image is generated using the mean filter in the spatial domain to create a noise image, which is the subtraction of the two images. A binary image is then obtained from the noise image to count the defective pixels, and a statistical control chart that monitors the number of defective pixels identifies the panel defects. Two experiments were conducted with images collected from an organic light-emitting diode inspection process, and the proposed method showed excellent performance with respect to classification accuracy and processing time.",
author = "Jueun Kwak and Lee, {Ki Bum} and Jaeyeon Jang and Chang, {Kyong Soo} and Kim, {Chang Ouk}",
year = "2019",
month = "3",
day = "15",
doi = "10.1007/s10845-017-1304-8",
language = "English",
volume = "30",
pages = "1047--1055",
journal = "Journal of Intelligent Manufacturing",
issn = "0956-5515",
publisher = "Springer Netherlands",
number = "3",

}

Automatic inspection of salt-and-pepper defects in OLED panels using image processing and control chart techniques. / Kwak, Jueun; Lee, Ki Bum; Jang, Jaeyeon; Chang, Kyong Soo; Kim, Chang Ouk.

In: Journal of Intelligent Manufacturing, Vol. 30, No. 3, 15.03.2019, p. 1047-1055.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automatic inspection of salt-and-pepper defects in OLED panels using image processing and control chart techniques

AU - Kwak, Jueun

AU - Lee, Ki Bum

AU - Jang, Jaeyeon

AU - Chang, Kyong Soo

AU - Kim, Chang Ouk

PY - 2019/3/15

Y1 - 2019/3/15

N2 - In the manufacture of flat display panels, salt-and-pepper defects are caused by a malfunction in the chemical process. The defects are characterized by the dispersion of many black and white pixels in the display panels; these pixels are difficult to detect with conventional automatic fault detection methods that specialize in recognizing certain shapes, such as line or mura defects (stains). This study proposes a simple but high-performance salt-and-pepper defect detection method. First, the background image of the original image is generated using the mean filter in the spatial domain to create a noise image, which is the subtraction of the two images. A binary image is then obtained from the noise image to count the defective pixels, and a statistical control chart that monitors the number of defective pixels identifies the panel defects. Two experiments were conducted with images collected from an organic light-emitting diode inspection process, and the proposed method showed excellent performance with respect to classification accuracy and processing time.

AB - In the manufacture of flat display panels, salt-and-pepper defects are caused by a malfunction in the chemical process. The defects are characterized by the dispersion of many black and white pixels in the display panels; these pixels are difficult to detect with conventional automatic fault detection methods that specialize in recognizing certain shapes, such as line or mura defects (stains). This study proposes a simple but high-performance salt-and-pepper defect detection method. First, the background image of the original image is generated using the mean filter in the spatial domain to create a noise image, which is the subtraction of the two images. A binary image is then obtained from the noise image to count the defective pixels, and a statistical control chart that monitors the number of defective pixels identifies the panel defects. Two experiments were conducted with images collected from an organic light-emitting diode inspection process, and the proposed method showed excellent performance with respect to classification accuracy and processing time.

UR - http://www.scopus.com/inward/record.url?scp=85012284370&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85012284370&partnerID=8YFLogxK

U2 - 10.1007/s10845-017-1304-8

DO - 10.1007/s10845-017-1304-8

M3 - Article

VL - 30

SP - 1047

EP - 1055

JO - Journal of Intelligent Manufacturing

JF - Journal of Intelligent Manufacturing

SN - 0956-5515

IS - 3

ER -