ORIGINAL RESEARCH article
Front. Phys.
Sec. Radiation Detectors and Imaging
Volume 13 - 2025 | doi: 10.3389/fphy.2025.1613119
Neutrosophic Set-based Defect Detection Method for CSP LED Images
Provisionally accepted
- Artificial Intelligence Research Institute, Shaoxing University, Shaoxing, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Chip scale package (CSP) light-emitting diode (LED) is miniaturized light-emitting diodes designed for automated chip-level packaging. Defect detection is particularly challenging due to the high density and small size of CSP LED beads on a strip. This paper presents a neutrosophic set-based defect detection method (ND) to identify the defective beads on CSP LED images. Firstly, the proposed ND method applies the neutrosophic set to discribe the uncertainty in CSP LED images, and then converts the CSP LED images into the neutrosophic images. Moreover, it employs the similarity operation to handle the image noises and then utilizes an enhancement operation to enhance image contrast to ultimately generates smoother images. Finally, these smoother images are used to calculate the pass rates by checking the gray values. Experimental results demonstrate that the proposed ND method can accurately and reliably detect defective beads in CSP LED images across various exposure times. Moreover, it provides a more robust estimate of pass rate compared with five traditional detection methods.
Keywords: Chip scale package, position estimation, Neutrosophic set, similarity operations, Defect detection
Received: 16 Apr 2025; Accepted: 21 Jul 2025.
Copyright: © 2025 Fan, Gong, Wu and Fan. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Junqi Gong, Artificial Intelligence Research Institute, Shaoxing University, Shaoxing, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.