Cryptology ePrint Archive: Report 2020/366

FICS-PCB: A Multi-Modal Image Dataset for Automated Printed Circuit Board Visual Inspection

Hangwei Lu and Dhwani Mehta and Olivia Paradis and Navid Asadizanjani and Mark Tehranipoor and Damon L. Woodard

Abstract: Over the years, computer vision and machine learn- ing disciplines have considerably advanced the field of automated visual inspection for Printed Circuit Board (PCB-AVI) assurance. However, in practice, the capabilities and limitations of these advancements remain unknown because there are few publicly accessible datasets for PCB visual inspection and even fewer that contain images that simulate realistic application scenarios. To address this need, we propose a publicly available dataset, FICS-PCB, to facilitate the development of robust methods for PCB-AVI. The proposed dataset includes challenging cases from three variable aspects: illumination, image scale, and image sensor. This dataset consists of 9,912 images of 31 PCB samples and contains 77,347 annotated components. This paper reviews the existing datasets and methodologies used for PCB- AVI, discusses challenges, describes the proposed dataset, and presents baseline performances using feature engineering and deep learning methods for PCB component classification.

Category / Keywords: foundations / PCB dataset, Automated Visual Inspection

Date: received 29 Mar 2020, last revised 16 Jul 2020

Contact author: qslvhw at ufl edu

Available format(s): PDF | BibTeX Citation

Note: Data link added.

Version: 20200717:035825 (All versions of this report)

Short URL: ia.cr/2020/366


[ Cryptology ePrint archive ]