Automated optical inspection (AOI) for printed circuit boards (PCBs) requires localizing small, sparse defects under illumination drift and minor placement misalignment, while supporting fast, auditable pass/fail decisions. This paper presents a training-free, reference-based digital image processing framework with no learning/training stage that compares each defective query image with a small library of defect-free reference templates (for the same PCB layout/revision) using a small set of interpretable control parameters. A reference is selected by coarse-to-fine matching (fast pre-screening followed by SSIM refinement on a central region), and an optional global alignment is applied only when it increases SSIM to limit defect-driven over-correction. Defects are highlighted by a defect-likelihood field that fuses an SSIM-derived structural dissimilarity map with a normalized absolute-difference map, followed by connected-component extraction to produce confidence-ranked bounding boxes. The method achieves Precision = 0.9663, Recall = 0.9987, and F1 = 0.9822 at the best-F1 operating point (0.149 false positives per image). Under the adopted box-matching protocol, average precision reaches 0.984. Precision–recall and FROC curves are reported to support threshold selection under different false-alarm budgets.
The ability to detect and localize the direction of the source of sounds has been with humans since ancient times, as humans can tell the direction of the sound coming from both the horizontal plane and vertical plane. Recent theory on why humans can distinguish the direction of the sound in the vertical plane is due to the difference between sounds reflected in human ears, more specifically, the pinna, which distort the sound in both the frequency domain and the time domain. In this paper, we will explore more on how to use the distortion in the time domain to localize the sound in the vertical plane. By analyzing the sound that is reflected in one of the artificial ears in the time domain, we use those data as a model to determine the sound coming from the vertical plane. The average angular error of the model is 4.86 degrees, with an RMSE of 6.90. The result confirms that we can analyze the sound in the time domain to determine the sound source direction in the vertical plane analyzed from only one microphone in the artificial ear.