Symlets-Based Trainable Wavelet Downsampling for YOLOv12s in PCB Defect Inspection
學年 114
學期 2
發表日期 2026-05-27
作品名稱 Symlets-Based Trainable Wavelet Downsampling for YOLOv12s in PCB Defect Inspection
作品名稱（其他語言）
著者 Ching-Ming Chang；Chii-Jen Chen
作品所屬單位
出版者
會議名稱 The International Conference on Recent Advancements in Computing in AI, IoT and Computer Engineering Technology (CICET 2026)
會議地點 New Taipei, Taiwan
摘要 Automated optical inspection (AOI) of printed circuit boards (PCBs) requires detectors that can accurately localize defects with diverse scales and irregular shapes while remaining lightweight enough for deployment on production lines. Recent YOLO-series detectors have achieved strong performance on PCB defect benchmarks; however, most improvements focus on attention mechanisms, feature fusion, or loss functions, while the downsampling operator in the neck is rarely revisited. In this paper, we propose a Symlets-based trainable wavelet downsampling module, termed SMD, and integrate it into YOLOv12s neck to better preserve high-frequency details in the feature maps. SMD constructs 2-D 4N×4N kernels from analytic 1-D Symlets filters and initializes the stride-2 convolutions before the detection heads, allowing the network to learn task-adapted wavelet filters while preserving desirable multi-resolution properties. Experiments on the DsPCBSD+ dataset further compare two insertion locations(before the large-scale head and the middle-scale head), and results show that inserting SMD before the large-scale head provides the most favorable trade-off over the YOLOv12s baseline.
關鍵字 Printed circuit board (PCB) defect detection, automated optical inspection (AOI), YOLOv12s, wavelet downsampling, Symlets, deep learning, object detection.
語言 en_US
收錄於
會議性質 國際
校內研討會地點 淡水校園
研討會時間 20260527~20260529
通訊作者 Chii-Jen Chen
國別 TWN
公開徵稿
出版型式
出處