A review of SMD-PCB defects and detection algorithms

Ahmad Fadzil Mohd Hani; Aamir Saeed Malik; Raja Kamil; Chung-Mun Thong

doi:10.1117/12.920531

13 January 2012 A review of SMD-PCB defects and detection algorithms

Ahmad Fadzil Mohd Hani, Aamir Saeed Malik, Raja Kamil, Chung-Mun Thong

Proceedings Volume 8350, Fourth International Conference on Machine Vision (ICMV 2011): Computer Vision and Image Analysis; Pattern Recognition and Basic Technologies; 83501P (2012) https://doi.org/10.1117/12.920531
Event: Fourth International Conference on Machine Vision (ICMV 11), 2011, Singapore, Singapore

Abstract

Detection and classification of defects on surface mount device printed circuit board (SMD-PCB) is an important requirement in electronic manufacturing process. This process which is primarily performed by automatic optical inspection (AOI) system ensures the functionality and quality of manufactured products. In this paper, the pattern recognition algorithms proposed in the literature for the inspection of defects using AOI are reviewed. The review focuses on segmentation algorithms, choice of features and feature extraction algorithms as well as the types of classifier and their relative classification performance. The review spans a 20 year period from 1990 to 2011. The results of the review suggest that solder joint defect is the type of defects mostly investigated and that the trend is moving towards combining the results of more than one classifier to improve classification accuracy and robustness.

Citation Download Citation

Ahmad Fadzil Mohd Hani, Aamir Saeed Malik, Raja Kamil, and Chung-Mun Thong "A review of SMD-PCB defects and detection algorithms", Proc. SPIE 8350, Fourth International Conference on Machine Vision (ICMV 2011): Computer Vision and Image Analysis; Pattern Recognition and Basic Technologies, 83501P (13 January 2012); https://doi.org/10.1117/12.920531

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available