ABSTRACT
Printed circuit board (PCB) may display diverse surface defects in manufacturing. These defects not only influence aesthetics but can also affect the performance of the PCB and potentially damage the entire board. Thus, achieving efficient and highly accurate detection of PCB surface defects is fundamental for quality control in fabrication. The rapidly advancing deep learning (DL) technology holds promising prospects for providing accurate and efficient detection methods for surface defects on PCB. To facilitate DL model training, it is imperative to compile a comprehensive dataset encompassing diverse surface defect types found on PCB at a significant scale. This work categorized PCB surface defects into 9 distinct categories based on factors such as their causes, locations, and morphologies and developed a dataset of PCB surface defect (DsPCBSD+). In DsPCBSD+, a total of 20,276 defects were annotated manually by bounding boxes on the 10,259 images. This openly accessible dataset is aimed accelerating and promoting further researches and advancements in the field of DL-based detection of PCB surface defect.
ABSTRACT
Broken cane and impurities such as top, leaf in harvested raw sugarcane significantly influence the yield of the sugar manufacturing process. It is crucial to determine the breakage and impurity ratios for assessing the quality and price of raw sugarcane in sugar refineries. However, the traditional manual sampling approach for detecting breakage and impurity ratios suffers from subjectivity, low efficiency, and result discrepancies. To address this problem, a novel approach combining an estimation model and semantic segmentation method for breakage and impurity ratios detection was developed. A machine vision-based image acquisition platform was designed, and custom image and mass datasets of cane, broken cane, top, and leaf were created. For cane, broken cane, top, and leaf, normal fitting of mean surface densities based on pixel information and measured mass was conducted. An estimation model for the mass of each class and the breakage and impurity ratios was established using the mean surface density and pixels. Furthermore, the MDSC-DeepLabv3+ model was developed to accurately and efficiently segment pixels of the four classes of objects. This model integrates improved MobileNetv2, atrous spatial pyramid pooling with deepwise separable convolution and strip pooling module, and coordinate attention mechanism to achieve high segmentation accuracy, deployability, and efficiency simultaneously. Experimental results based on the custom image and mass datasets showed that the estimation model achieved high accuracy for breakage and impurity ratios between estimated and measured value with R2 values of 0.976 and 0.968, respectively. MDSC-DeepLabv3+ outperformed the compared models with mPA and mIoU of 97.55% and 94.84%, respectively. Compared to the baseline DeepLabv3+, MDSC-DeepLabv3+ demonstrated significant improvements in mPA and mIoU and reduced Params, FLOPs, and inference time, making it suitable for deployment on edge devices and real-time inference. The average relative errors of breakage and impurity ratios between estimated and measured values were 11.3% and 6.5%, respectively. Overall, this novel approach enables high-precision, efficient, and intelligent detection of breakage and impurity ratios for raw sugarcane.
