Global contextual attention augmented YOLO with ConvMixer prediction heads for PCB surface defect detection

Xia, Kewen; Lv, Zhongliang; Liu, Kang; Lu, Zhenyu; Zhou, Chuande; Zhu, Hong; Chen, Xuanlin

doi:10.1038/s41598-023-36854-2

Cited by 26 publications

(4 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…TP means true positive, FP means false positive, FN means false negative, and TN means true negative. The corresponding formulas are illustrated in equations ( 4) to ( 8) [40]. Precision indicates the ratio of correctly identified positive instances among the instances classified as positive, and it is computed as follows:…”

Section: Evaluation Metricsmentioning

confidence: 99%

Lightweight Detection Model RM-LFPN-YOLO for Rebar Counting

Liu,

Cheng,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

In this study, we propose a novel lightweight detection model for rebar counting, which is rectified mobilenet lightweight feature pyramid network based on YOLO (RM-LFPN-YOLO). The model incorporates a lightweight backbone network that integrates the coordinate attention (CA) mechanism, a lightweight feature pyramid network (LFPN), and a loss function that combines focal loss and efficient intersection over union (EIOU) loss, all meticulously designed to enhance the model's performance. Experimental results demonstrate that our improved algorithm, with a mere 25.08M parameters, computes efficiently at 7.60G with an input size of 416 pixels. Additionally, it achieves an impressive average precision (AP) of 99.03% at an IOU of 0.5. The proposed lightweight model can be deployed on embedded devices and achieve efficient rebar detection and counting performance.

show abstract

Section: Evaluation Metricsmentioning

confidence: 99%

Lightweight Detection Model RM-LFPN-YOLO for Rebar Counting

Liu,

Cheng,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…(4) Model Average Precision (Mean Average Precision): indicates the average of AP values for all categories in the dataset, as in equation (10).…”

Section: Tp R Tp Fn = + (8)mentioning

confidence: 99%

“…Li [9] employed a composite training dataset comprising both virtual and real PCB images derived from synthetic data, enhancing detection accuracy by appending an additional output layer to the original YOLOv3 architecture. Xia [10] introduced contextual attention into the YOLOv5s model, significantly mitigating the challenges of missed detections and false positives, particularly in the context of small targets and complex background textures. By implementing a compressed training methodology and integrating a micro detection head, Zhou [11] further augmented YOLOv5's proficiency in recognizing small targets, all while preserving rapid recognition speeds.…”

Section: Introductionmentioning

confidence: 99%

Enhanced Small Defect Detection on PCBs Using Lightweight YOLOv5s with Hierarchical Clustering and Dynamic Feature Pyramid Network

Zhou,

Lu,

2024

Preprint

View full text Add to dashboard Cite

An enhanced clustering technique integrated with the YOLOv5s model addresses the challenges of detecting small defect targets on Printed Circuit Boards (PCBs), which are often difficult to locate and prone to high false detection rates. Initially, the method improves the original K-means algorithm by employing a self-developed Hierarchical Density-Based K-means (HDBK-means) algorithm to re-cluster and generate anchor boxes better suited to PCB fault characteristics. Secondly, it replaces the Concentrated-Comprehensive Convolution (C3) module with a novel combination of the Reparameterized Normalized Cross-Stage Partial Efficient Layer Aggregation Network (RepNCSPELAN) module and Spatial and Channel Reconstruction Convolution (SCConv), reducing the model's computational cost without compromising accuracy. Furthermore, the network is enhanced with an adaptive feature selection module to boost its performance in recognizing small targets. Lastly, the GDFPN (Generalized Dynamic Feature Pyramid Network) is used to achieve information interaction across different scales. further enhancing the network's detection accuracy. Comparative studies were conducted on a public PCB dataset. The experimental results demonstrate that the proposed algorithm achieves a mAP (mean Average Precision) of 98.6%, an accuracy of 99.2%, a model size of 10.9M, and an FPS (Frames Per Second) of 138.1. Compared to the original model, the proposed algorithm improves the mAP by 3.8% and the Precision (P) by 2.9%, while reducing the model size by 20.4%, thus fulfilling the requirements for easy deployment.

show abstract

“…In the industrial production of hot-rolled steel strips 1 – 7 , defect detection is a crucial task in the manufacturing domain. Its primary objective is to use automation and computer vision techniques to detect and identify defects, flaws, or anomalies in the manufacturing process.…”

Section: Introductionmentioning

confidence: 99%

Surface defect detection of hot rolled steel based on multi-scale feature fusion and attention mechanism residual block

Zhang,

Li,

Miao

et al. 2024

Sci Rep

View full text Add to dashboard Cite

To improve the precision of defect categorization and localization in images, this paper proposes an approach for detecting surface defects in hot-rolled steel strips. The approach uses an improved YOLOv5 network model to overcome the issues of inadequate feature extraction capacity and suboptimal feature integration when identifying surface defects on steel strips. The proposed method achieves higher detection accuracy and localization precision, making it more competitive and applicable in real production. Firstly, the multi-scale feature fusion (MSF) strategy is utilized to fuse shallow and deep features effectively and enrich detailed information relevant to target defects. Secondly, the CSPLayer Res2Attention block (CRA block) residual module is introduced to reduce the loss of defect information during hierarchical transmission, thereby enhancing the extraction of fine-grained features and improving the perception of details and global features. Finally, the experimental results indicate that the mAP on the NEU-DET and GC10-DET datasets approaches 78.5% and 67.3%, respectively, which is 4.9% and 2.1% higher than that of the baseline. Meanwhile, it has higher precision and more precise localization capabilities than other methods. Furthermore, it also achieves 59.2% mAP on the APDDD dataset, indicating its potential for growth in further domains.

show abstract

Global contextual attention augmented YOLO with ConvMixer prediction heads for PCB surface defect detection

Cited by 26 publications

References 39 publications

Lightweight Detection Model RM-LFPN-YOLO for Rebar Counting

Lightweight Detection Model RM-LFPN-YOLO for Rebar Counting

Enhanced Small Defect Detection on PCBs Using Lightweight YOLOv5s with Hierarchical Clustering and Dynamic Feature Pyramid Network

Surface defect detection of hot rolled steel based on multi-scale feature fusion and attention mechanism residual block

Contact Info

Product

Resources

About