An Improved YOLOv5 Network for Detection of Printed Circuit Board Defects

Niu, Jie; Li, Hongyan; Chen, Xu; Qian, Kun

doi:10.1155/2023/7270093

Cited by 9 publications

(4 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Xin et al discuss an enhanced Printed Circuit Board (PCB) electronic component defect detection method centered on the YOLOv4 algorithm [3]. Niu et al contend that the traditional manual detection methods for PCB defects usually suffer from an increased error rate and fail to meet production standards as a result of amplified demands for electronic products [4]. Xin et al leverages deep learning (DL) techniques and a PCB defect dataset from the Intelligent Robot Laboratory of Perking University to address these challenges.…”

Section: The Defect Detection Methods Of Pcb Componentsmentioning

confidence: 99%

Circuit defect detection based on AI deep learning

Wang

2023

TNS

View full text Add to dashboard Cite

In the milieu of promptly advancing technology and increasing demand for electronic devices, circuit defect detection has become crucial to warranting product quality. This study tackles the cons of traditional defect detection methods, proposing a mind-boggling approach based on AI deep learning. The study intends to establish and enhance deep learning algorithms for the exact and real-time detection of circuit defects. This research encompasses an in-depth review of existing literature on circuit defect detection and AI deep learning, underlining the existing gaps and pitfalls in the field. The study will primarily deploy convolutional neural networks (CNNs) and recurrent neural networks (RNNs) as the primary tools to process various data modalities. The results highlight that the proposed AI deep learning framework depicts grander performance, unlike in traditional manual inspection. The study sets precedence in AI applications in quality control as it contributes to improved manufacturing efficiency, reduced production costs, and delivery of utmost-quality electronic products to consumers.

show abstract

Section: The Defect Detection Methods Of Pcb Componentsmentioning

confidence: 99%

Circuit defect detection based on AI deep learning

Wang

2023

TNS

View full text Add to dashboard Cite

show abstract

“…Furthermore, the Focal-EIOU loss function is employed as a replacement for GIOU to address the degradation issue, thereby improving the localization capability of PCB defects. 17 Li et al introduce feedback connections during the feature fusion stage to facilitate better transmission of details and local information within the network. They propose the SEIoU loss function, which integrates both positional information and IoU to calculate the position loss between predicted boxes and ground truth boxes, thereby enhancing the PCB defect detection capability.…”

Section: Introductionmentioning

confidence: 99%

“…utilize the K-means++ method to enhance the matching of prior anchor boxes. Furthermore, the Focal-EIOU loss function is employed as a replacement for GIOU to address the degradation issue, thereby improving the localization capability of PCB defects 17 . Li et al.…”

Section: Introductionmentioning

confidence: 99%

WDC-YOLO: an improved YOLO model for small objects oriented printed circuit board defect detection

Song,

Wang,

et al. 2024

J. Electron. Imag.

View full text Add to dashboard Cite

The detection of surface defects on a printed circuit board (PCB) plays a crucial role in ensuring the quality of PCB products. To address the diversity of defect poses and the challenges associated with detecting small objects on PCB, this paper proposes an improved YOLOv7 model for small objects-oriented PCB defect detection. First, this paper improves the regression loss function of YOLOv7 by incorporating wise-IoU (WIoU) and replacing IoU with an outlier degree to develop a gradient-boosting allocation strategy, thereby increasing the network's accuracy. Second, this paper proposes a coordinate attention dynamic mechanism that performs convolution operations with deformable convolutional networks v2 (DCNv2) using coordinate attention. This mechanism effectively suppresses redundant information. Finally, this paper proposes a dynamic head diverse (DyHead-d) module that prioritizes spatial awareness over scale awareness, building on DyHead. This module improves the network's ability to localize small targets. Experimental results show that the WDC-YOLO achieves a mean average precision of 98.4% on public datasets, demonstrating a 3.1% improvement compared to the original network. The significantly enhanced detection accuracy meets the real-time requirements of PCB defect diagnosis, which is of great importance for quality control and cost reduction in PCB industrial production.

show abstract

“…As for the low-efficiency traditional sorting of PCB defects in the semiconductor industry, a supervised learning-based model was applied to sort PCB defect detection by Pham et al [8]. The K-means clustering segmentation algorithm was used by Niu et al [9] to detect the bare PCB, which aimed to improve the detection accuracy and speed. As for the characteristics of fuzziness and noise in PCB optoelectronic images, a circle detection method of the images was proposed by Qiao et al [10,11] based on the improved Hough transform.…”

Section: Introductionmentioning

confidence: 99%

Comparison of Object Region Segmentation Algorithms of PCB Defect Detection

Zhang¹,

Xiao²,

Fu³

2023

View full text Add to dashboard Cite

As a core component of electronic products in industrial production, the printed circuit board (PCB) is highly integrated, and carries various electronic components and complex wire layout. Although the PCB has a small size, its defect detection directly affects the quality of circuit board, which is of great significance. This research aimed to study PCB defect detection based on machine vision technology, because the product quality inspection requirements have been continuously increasing in industrial modernization. Whether the object region segmentation algorithms are fast, effective, and accurate directly affects the effects and efficiency of subsequent machine vision defect detection, because object region segmentation is a key step in PCB defect detection. Three types of object region segmentation algorithms, namely, color space threshold segmentation, morphological edge detection segmentation, and K-means clustering segmentation, were studied, and their advantages and disadvantages were analyzed in detail. A suitable algorithm was selected for detection object through experiments, which laid the foundation for better algorithm improvement and segmented object regions quickly and accurately in the defect detection process.

show abstract

An Improved YOLOv5 Network for Detection of Printed Circuit Board Defects

Cited by 9 publications

References 40 publications

Circuit defect detection based on AI deep learning

Circuit defect detection based on AI deep learning

WDC-YOLO: an improved YOLO model for small objects oriented printed circuit board defect detection

Comparison of Object Region Segmentation Algorithms of PCB Defect Detection

Contact Info

Product

Resources

About