A Two-Step Classification Method for Painting Defects Using Deep Learning

Kazune Adachi; Takahiro Natori; Naoyuki Aikawa

doi:10.1109/ICEIC54506.2022.9748794

A Two-Step Classification Method for Painting Defects Using Deep Learning

Kazune Adachi, Takahiro Natori, Naoyuki Aikawa

Department of Applied Electronics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In the visual inspection process of product manu-facturing, the inspection results may vary depending on the skill level and fatigue level of the inspectors. Therefore, quality assur-ance is difficult. Recently, a method for visual inspection using image processing based on deep learning has been proposed. In this paper, we use image processing to detect coating defects, automatically generate data for deep learning, and use the data to classify the defects using deep learning. In particular, we aim to achieve more accurate classification by performing two-step classification.

Original language	English
Title of host publication	2022 International Conference on Electronics, Information, and Communication, ICEIC 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665409346
DOIs	https://doi.org/10.1109/ICEIC54506.2022.9748794
Publication status	Published - 2022
Event	2022 International Conference on Electronics, Information, and Communication, ICEIC 2022 - Jeju, Korea, Republic of Duration: 6 Feb 2022 → 9 Feb 2022

Publication series

Name	2022 International Conference on Electronics, Information, and Communication, ICEIC 2022

Conference

Conference	2022 International Conference on Electronics, Information, and Communication, ICEIC 2022
Country/Territory	Korea, Republic of
City	Jeju
Period	6/02/22 → 9/02/22

Keywords

Deep learning
Image processing
Painting defects
two-step classification
Visual inspection

Access to Document

10.1109/ICEIC54506.2022.9748794

Cite this

Adachi, K., Natori, T., & Aikawa, N. (2022). A Two-Step Classification Method for Painting Defects Using Deep Learning. In 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022 (2022 International Conference on Electronics, Information, and Communication, ICEIC 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICEIC54506.2022.9748794

Adachi, Kazune ; Natori, Takahiro ; Aikawa, Naoyuki. / A Two-Step Classification Method for Painting Defects Using Deep Learning. 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (2022 International Conference on Electronics, Information, and Communication, ICEIC 2022).

@inproceedings{ba109a8590254d0eab92f5809e76ba50,

title = "A Two-Step Classification Method for Painting Defects Using Deep Learning",

abstract = "In the visual inspection process of product manu-facturing, the inspection results may vary depending on the skill level and fatigue level of the inspectors. Therefore, quality assur-ance is difficult. Recently, a method for visual inspection using image processing based on deep learning has been proposed. In this paper, we use image processing to detect coating defects, automatically generate data for deep learning, and use the data to classify the defects using deep learning. In particular, we aim to achieve more accurate classification by performing two-step classification. ",

keywords = "Deep learning, Image processing, Painting defects, two-step classification, Visual inspection",

author = "Kazune Adachi and Takahiro Natori and Naoyuki Aikawa",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022 ; Conference date: 06-02-2022 Through 09-02-2022",

year = "2022",

doi = "10.1109/ICEIC54506.2022.9748794",

language = "English",

series = "2022 International Conference on Electronics, Information, and Communication, ICEIC 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2022 International Conference on Electronics, Information, and Communication, ICEIC 2022",

}

Adachi, K, Natori, T & Aikawa, N 2022, A Two-Step Classification Method for Painting Defects Using Deep Learning. in 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022. 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022, Institute of Electrical and Electronics Engineers Inc., 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022, Jeju, Korea, Republic of, 6/02/22. https://doi.org/10.1109/ICEIC54506.2022.9748794

A Two-Step Classification Method for Painting Defects Using Deep Learning. / Adachi, Kazune; Natori, Takahiro; Aikawa, Naoyuki.
2022 International Conference on Electronics, Information, and Communication, ICEIC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (2022 International Conference on Electronics, Information, and Communication, ICEIC 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Two-Step Classification Method for Painting Defects Using Deep Learning

AU - Adachi, Kazune

AU - Natori, Takahiro

AU - Aikawa, Naoyuki

PY - 2022

Y1 - 2022

N2 - In the visual inspection process of product manu-facturing, the inspection results may vary depending on the skill level and fatigue level of the inspectors. Therefore, quality assur-ance is difficult. Recently, a method for visual inspection using image processing based on deep learning has been proposed. In this paper, we use image processing to detect coating defects, automatically generate data for deep learning, and use the data to classify the defects using deep learning. In particular, we aim to achieve more accurate classification by performing two-step classification.

AB - In the visual inspection process of product manu-facturing, the inspection results may vary depending on the skill level and fatigue level of the inspectors. Therefore, quality assur-ance is difficult. Recently, a method for visual inspection using image processing based on deep learning has been proposed. In this paper, we use image processing to detect coating defects, automatically generate data for deep learning, and use the data to classify the defects using deep learning. In particular, we aim to achieve more accurate classification by performing two-step classification.

KW - Deep learning

KW - Image processing

KW - Painting defects

KW - two-step classification

KW - Visual inspection

UR - http://www.scopus.com/inward/record.url?scp=85128863925&partnerID=8YFLogxK

U2 - 10.1109/ICEIC54506.2022.9748794

DO - 10.1109/ICEIC54506.2022.9748794

M3 - Conference contribution

AN - SCOPUS:85128863925

T3 - 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022

BT - 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022

Y2 - 6 February 2022 through 9 February 2022

ER -

Adachi K, Natori T, Aikawa N. A Two-Step Classification Method for Painting Defects Using Deep Learning. In 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022. Institute of Electrical and Electronics Engineers Inc. 2022. (2022 International Conference on Electronics, Information, and Communication, ICEIC 2022). doi: 10.1109/ICEIC54506.2022.9748794

A Two-Step Classification Method for Painting Defects Using Deep Learning

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this