AUTHOR=Fan En , Gong Junqi , Wu Zhenxin , Lv Qinlong , Fan Changxing 

TITLE=Neutrosophic set-based defect detection method for CSP LED images

JOURNAL=Frontiers in Physics

VOLUME=Volume 13 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/physics/articles/10.3389/fphy.2025.1613119

DOI=10.3389/fphy.2025.1613119

ISSN=2296-424X

ABSTRACT=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.