A Real-time PCB Defect Detector Based on Supervised and Semi-supervised Learning

Fan He; Sanli Tang; Siamak Mehrkanoon; Xiaolin Huang; Yie Yang

A Real-time PCB Defect Detector Based on Supervised and Semi-supervised Learning

Fan He, Sanli Tang, Siamak Mehrkanoon, Xiaolin Huang, Yie Yang

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

Abstract

This paper designs a deep model to detect PCB defects from an input pair of a detect-free template and a defective tested image. A novel group pyramid pooling module is proposed to efficiently extract features in various resolutions to predict defects in different scales. To train the deep model, a dataset including 6 common types of PCB defects is established, namely DeepPCB, which contains 1,500 image pairs with annotations. Besides, a semi-supervised learning manner is examined to effectively utilize the unlabelled images for training the PCB defect detector. Experiment results validate the effectiveness and efficiency of the proposed model by achieving 98.6% mAP @ 62 FPS on DeepPCB dataset. DeepPCB is now available at: https://github.com/tangsanli5201/DeepPCB.

Original language	English
Title of host publication	ESANN 2020 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Pages	527-532
Publication status	Published - 2020
Event	European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning - Online, Brugge, Belgium Duration: 2 Oct 2020 → 4 Oct 2020 Conference number: 28 https://www.esann.org/esann20programme

Symposium

Symposium	European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Abbreviated title	ESANN 2020
Country/Territory	Belgium
City	Brugge
Period	2/10/20 → 4/10/20
Internet address	https://www.esann.org/esann20programme

Access to Document

https://www.esann.org/sites/default/files/proceedings/2020/ES2020-33.pdf

Cite this

@inproceedings{10bfe5ca43f14e41b65791392947bbfb,

title = "A Real-time PCB Defect Detector Based on Supervised and Semi-supervised Learning",

abstract = "This paper designs a deep model to detect PCB defects from an input pair of a detect-free template and a defective tested image. A novel group pyramid pooling module is proposed to efficiently extract features in various resolutions to predict defects in different scales. To train the deep model, a dataset including 6 common types of PCB defects is established, namely DeepPCB, which contains 1,500 image pairs with annotations. Besides, a semi-supervised learning manner is examined to effectively utilize the unlabelled images for training the PCB defect detector. Experiment results validate the effectiveness and efficiency of the proposed model by achieving 98.6% mAP @ 62 FPS on DeepPCB dataset. DeepPCB is now available at: https://github.com/tangsanli5201/DeepPCB.",

author = "Fan He and Sanli Tang and Siamak Mehrkanoon and Xiaolin Huang and Yie Yang",

note = "Publisher Copyright: {\textcopyright} ESANN 2020 - Proceedings, 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning.; European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2020 ; Conference date: 02-10-2020 Through 04-10-2020",

year = "2020",

language = "English",

isbn = "978-2-87587-074-2",

pages = "527--532",

booktitle = "ESANN 2020 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning",

url = "https://www.esann.org/esann20programme",

}

He, F, Tang, S, Mehrkanoon, S, Huang, X & Yang, Y 2020, A Real-time PCB Defect Detector Based on Supervised and Semi-supervised Learning. in ESANN 2020 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. pp. 527-532, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Brugge, Belgium, 2/10/20. <https://www.esann.org/sites/default/files/proceedings/2020/ES2020-33.pdf>

A Real-time PCB Defect Detector Based on Supervised and Semi-supervised Learning. / He, Fan; Tang, Sanli; Mehrkanoon, Siamak et al.
ESANN 2020 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. 2020. p. 527-532.

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

TY - GEN

T1 - A Real-time PCB Defect Detector Based on Supervised and Semi-supervised Learning

AU - He, Fan

AU - Tang, Sanli

AU - Mehrkanoon, Siamak

AU - Huang, Xiaolin

AU - Yang, Yie

N1 - Conference code: 28

PY - 2020

Y1 - 2020

N2 - This paper designs a deep model to detect PCB defects from an input pair of a detect-free template and a defective tested image. A novel group pyramid pooling module is proposed to efficiently extract features in various resolutions to predict defects in different scales. To train the deep model, a dataset including 6 common types of PCB defects is established, namely DeepPCB, which contains 1,500 image pairs with annotations. Besides, a semi-supervised learning manner is examined to effectively utilize the unlabelled images for training the PCB defect detector. Experiment results validate the effectiveness and efficiency of the proposed model by achieving 98.6% mAP @ 62 FPS on DeepPCB dataset. DeepPCB is now available at: https://github.com/tangsanli5201/DeepPCB.

AB - This paper designs a deep model to detect PCB defects from an input pair of a detect-free template and a defective tested image. A novel group pyramid pooling module is proposed to efficiently extract features in various resolutions to predict defects in different scales. To train the deep model, a dataset including 6 common types of PCB defects is established, namely DeepPCB, which contains 1,500 image pairs with annotations. Besides, a semi-supervised learning manner is examined to effectively utilize the unlabelled images for training the PCB defect detector. Experiment results validate the effectiveness and efficiency of the proposed model by achieving 98.6% mAP @ 62 FPS on DeepPCB dataset. DeepPCB is now available at: https://github.com/tangsanli5201/DeepPCB.

M3 - Conference article in proceeding

SN - 978-2-87587-074-2

SP - 527

EP - 532

BT - ESANN 2020 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

T2 - European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

Y2 - 2 October 2020 through 4 October 2020

ER -