This paper exploits a wavelet-based scheme to inspect the surface defects and basic dimensions of 0805 Multi-layer Ceramic Chip capacitors (MLCC) using machine vision. The image of a passive component is initially processed to show only two solder plates (terminations). Then, the covariance matrix eigenvector for each boundary point generates the 1D h-p representation to describe the angle variations at the boundaries of each termination. The 1D h-p representation is further decomposed directly by a one-dimensional wavelet transform (1D WT). Since a single corner (an intersection of two boundary edges) and the jag corners (the surface defects) are local deviations on termination boundaries, their locations are represented as intensive and have a highly fluctuated wavelet energy at the 1st detail scale. Concerning a 0805 MLCC type of passive component, the surface defects and single corners on termination boundaries can be captured by appropriate thresholds (e.g., in wavelet energy). The basic dimensions of a passive component are simply the direct distance between located single corners. Real 0805 MLCCs are testing samples to evaluate the performance of the proposed approach. Experimental results show that the proposed method achieves a precise identification of the surface defects and measurements for basic dimensions. The proposed approach is invariant with respect to the orientation, easy to implement and free from a primitive-matching process. Therefore, it is especially suitable for various types of passive components that are similar to the 0805 MLCC in small-batch production.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.