TDD-net: a tiny defect detection network for printed circuit boards

Tiny defect detection (TDD) which aims to perform the quality control of printed circuit boards (PCBs) is a basic and essential task in the production of most electronic products. Though significant progress has been made in PCB defect detection, traditional methods are still difficult to cope with...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	CAAI Transactions on Intelligence Technology Ročník 4; číslo 2; s. 110 - 116
Hlavní autoři:	Ding, Runwei, Dai, Linhui, Li, Guangpeng, Liu, Hong
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Beijing The Institution of Engineering and Technology 01.06.2019 John Wiley & Sons, Inc Wiley
Témata:	Algorithms C5260B Computer vision and image processing techniques C6170K Knowledge engineering techniques C7480 Production engineering computing Circuit boards Clustering complex PCBs computer vision data mining Datasets deep convolutional networks Defects diverse PCBs E0410D Industrial applications of IT feature extraction Feature maps Hierarchies learning (artificial intelligence) neural nets Neural networks pattern clustering PCB defect dataset show PCB defect detection printed circuit boards Printed circuits production engineering computing Pyramids Quality control Research Article Similarity measures TDD-Net strengthens tiny defect detection network PCB defect detection complex PCBs quality control data mining production engineering computing PCB defect dataset show printed circuits tiny defect detection network pattern clustering diverse PCBs feature extraction computer vision deep convolutional networks printed circuit boards learning (artificial intelligence) TDD-Net strengthens neural nets
ISSN:	2468-2322, 2468-6557, 2468-2322
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Tiny defect detection (TDD) which aims to perform the quality control of printed circuit boards (PCBs) is a basic and essential task in the production of most electronic products. Though significant progress has been made in PCB defect detection, traditional methods are still difficult to cope with the complex and diverse PCBs. To deal with these problems, this article proposes a tiny defect detection network (TDD-Net) to improve performance for PCB defect detection. In this method, the inherent multi-scale and pyramidal hierarchies of deep convolutional networks are exploited to construct feature pyramids. Compared with existing approaches, the TDD-Net has three novel changes. First, reasonable anchors are designed by using k-means clustering. Second, TDD-Net strengthens the relationship of feature maps from different levels and benefits from low-level structural information, which is suitable for tiny defect detection. Finally, considering the small and imbalance dataset, online hard example mining is adopted in the whole training phase in order to improve the quality of region-of-interest (ROI) proposals and make more effective use of data information. Quantitative results on the PCB defect dataset show that the proposed method has better portability and can achieve 98.90% mAP, which outperforms the state-of-arts. The code will be publicly available.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ISSN:	2468-2322 2468-6557 2468-2322
DOI:	10.1049/trit.2019.0019