Image Blending Methods for Defective PCB Image Generation

Ting Hui Chiang; Chun Hao Chang; Li Hsin Chen; Chun Ju Lin; An Chun Luo; Yu Shan Deng; Po Han Chang; Ming Ji Dai; Yu Chee Tseng

doi:10.1109/ICCE-Taiwan55306.2022.9869213

Image Blending Methods for Defective PCB Image Generation

Ting Hui Chiang, Chun Hao Chang, Li Hsin Chen, Chun Ju Lin, An Chun Luo, Yu Shan Deng, Po Han Chang, Ming Ji Dai, Yu Chee Tseng

研究成果: Conference contribution › 同行評審

摘要

Recent works have shown that deep learning models effectively assist in the task of image classification, which is often applied in industrial problems, e.g., defective PCB detection. However, training a model for defect detection requires lots of training data, but nowadays, it is challenging to obtain defective samples due to the production line is stable and mature. Therefore, we design two defective PCB image generation methods for different defect types. The proposed generation methods can produce more defective PCB images as much as we want, and experimental results show that our proposed methods can generate realistic defective images.

原文	English
主出版物標題	Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022
發行者	Institute of Electrical and Electronics Engineers Inc.
頁面	261-262
頁數	2
ISBN（電子）	9781665470506
DOIs	https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869213
出版狀態	Published - 2022
事件	2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022 - Taipei, 台灣持續時間: 6 7月 2022 → 8 7月 2022

出版系列

名字	Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022

Conference

Conference	2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022
國家/地區	台灣
城市	Taipei
期間	6/07/22 → 8/07/22

UN SDG

此研究成果有助於以下永續發展目標

存取文件

10.1109/ICCE-Taiwan55306.2022.9869213

其它文件與鏈接

Link to publication in Scopus

引用此

Chiang, T. H., Chang, C. H., Chen, L. H., Lin, C. J., Luo, A. C., Deng, Y. S., Chang, P. H., Dai, M. J., & Tseng, Y. C. (2022). Image Blending Methods for Defective PCB Image Generation. 於 Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022 (頁 261-262). (Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869213

Chiang, Ting Hui ; Chang, Chun Hao ; Chen, Li Hsin 等. / Image Blending Methods for Defective PCB Image Generation. Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022. Institute of Electrical and Electronics Engineers Inc., 2022. 頁 261-262 (Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022).

@inproceedings{42fc35c80a5f443d9c83c1396b1f4ff8,

title = "Image Blending Methods for Defective PCB Image Generation",

abstract = "Recent works have shown that deep learning models effectively assist in the task of image classification, which is often applied in industrial problems, e.g., defective PCB detection. However, training a model for defect detection requires lots of training data, but nowadays, it is challenging to obtain defective samples due to the production line is stable and mature. Therefore, we design two defective PCB image generation methods for different defect types. The proposed generation methods can produce more defective PCB images as much as we want, and experimental results show that our proposed methods can generate realistic defective images.",

author = "Chiang, {Ting Hui} and Chang, {Chun Hao} and Chen, {Li Hsin} and Lin, {Chun Ju} and Luo, {An Chun} and Deng, {Yu Shan} and Chang, {Po Han} and Dai, {Ming Ji} and Tseng, {Yu Chee}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022 ; Conference date: 06-07-2022 Through 08-07-2022",

year = "2022",

doi = "10.1109/ICCE-Taiwan55306.2022.9869213",

language = "English",

series = "Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022",

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

pages = "261--262",

booktitle = "Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022",

address = "美國",

}

Chiang, TH, Chang, CH, Chen, LH, Lin, CJ, Luo, AC, Deng, YS, Chang, PH, Dai, MJ & Tseng, YC 2022, Image Blending Methods for Defective PCB Image Generation. 於 Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022. Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022, Institute of Electrical and Electronics Engineers Inc., 頁 261-262, 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022, Taipei, 台灣, 6/07/22. https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869213

Image Blending Methods for Defective PCB Image Generation. / Chiang, Ting Hui; Chang, Chun Hao; Chen, Li Hsin 等.
Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 261-262 (Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022).

研究成果: Conference contribution › 同行評審

TY - GEN

T1 - Image Blending Methods for Defective PCB Image Generation

AU - Chiang, Ting Hui

AU - Chang, Chun Hao

AU - Chen, Li Hsin

AU - Lin, Chun Ju

AU - Luo, An Chun

AU - Deng, Yu Shan

AU - Chang, Po Han

AU - Dai, Ming Ji

AU - Tseng, Yu Chee

PY - 2022

Y1 - 2022

N2 - Recent works have shown that deep learning models effectively assist in the task of image classification, which is often applied in industrial problems, e.g., defective PCB detection. However, training a model for defect detection requires lots of training data, but nowadays, it is challenging to obtain defective samples due to the production line is stable and mature. Therefore, we design two defective PCB image generation methods for different defect types. The proposed generation methods can produce more defective PCB images as much as we want, and experimental results show that our proposed methods can generate realistic defective images.

AB - Recent works have shown that deep learning models effectively assist in the task of image classification, which is often applied in industrial problems, e.g., defective PCB detection. However, training a model for defect detection requires lots of training data, but nowadays, it is challenging to obtain defective samples due to the production line is stable and mature. Therefore, we design two defective PCB image generation methods for different defect types. The proposed generation methods can produce more defective PCB images as much as we want, and experimental results show that our proposed methods can generate realistic defective images.

UR - http://www.scopus.com/inward/record.url?scp=85138719478&partnerID=8YFLogxK

U2 - 10.1109/ICCE-Taiwan55306.2022.9869213

DO - 10.1109/ICCE-Taiwan55306.2022.9869213

M3 - Conference contribution

AN - SCOPUS:85138719478

T3 - Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022

SP - 261

EP - 262

BT - Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022

Y2 - 6 July 2022 through 8 July 2022

ER -

Chiang TH, Chang CH, Chen LH, Lin CJ, Luo AC, Deng YS 等. Image Blending Methods for Defective PCB Image Generation. 於 Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 261-262. (Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022). doi: 10.1109/ICCE-Taiwan55306.2022.9869213

Image Blending Methods for Defective PCB Image Generation

摘要

出版系列

Conference

UN SDG

存取文件

其它文件與鏈接

指紋

引用此