Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jun 21;25(13):3859.
doi: 10.3390/s25133859.

RST-YOLOv8: An Improved Chip Surface Defect Detection Model Based on YOLOv8

Wenjie Tang  1 , Yangjun Deng  1   2   3 , Xu Luo  1
Affiliations

RST-YOLOv8: An Improved Chip Surface Defect Detection Model Based on YOLOv8

Wenjie Tang et al. Sensors (Basel). .

Abstract

Surface defect detection in chips is crucial for ensuring product quality and reliability. This paper addresses the challenge of low identification accuracy in chip surface defect detection, which arises from the similarity of defect characteristics, small sizes, and significant scale differences. We propose an enhanced chip surface defect detection algorithm based on an improved version of YOLOv8, termed RST-YOLOv8. This study introduces the C2f_RVB module, which incorporates RepViTBlock technology. This integration effectively optimizes feature representation capabilities while significantly reducing the model's parameter count. By enhancing the expressive power of deep features, we achieve a marked improvement in the identification accuracy of small defect targets. Additionally, we employ the SimAM attention mechanism, enabling the model to learn three-dimensional channel information, thereby strengthening its perception of defect characteristics. To address the issues of missed detections and false detections of small targets in chip surface defect detection, we designed a task-aligned dynamic detection head (TADDH) to facilitate interaction between the localization and classification detection heads. This design improves the accuracy of small target detection. Experimental evaluations on the PCB_DATASET indicate that our model improved the mAP@0.5 by 10.3%. Furthermore, significant progress was achieved in experiments on the chip surface defect dataset, where mAP@0.5 increased by 5.4%. Simultaneously, the model demonstrated significant advantages in terms of computational complexity, as both the number of parameters and GFLOPs were effectively controlled. This showcases the model's balance between high precision and a lightweight design. The experimental results show that the RST-YOLOv8 model has a significant advantage in detection accuracy for chip surface defects compared to other models. It not only enhances detection accuracy but also achieves an optimal balance between computational resource consumption and real-time performance, providing an ideal technical pathway for chip surface defect detection tasks.

Keywords: RST-YOLOv8; chip surface defect detection; feature representation; small object detection.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
RST-YOLOv8 network architecture.
Figure 2
Figure 2
RepViTBlock structure.
Figure 3
Figure 3
RepVGGDW structure.
Figure 4
Figure 4
C2f_RVB structure.
Figure 5
Figure 5
SimAM attention mechanism structure diagram.
Figure 6
Figure 6
TADDH structure.
Figure 7
Figure 7
Schematic diagram of task decomposition structure.
Figure 8
Figure 8
PCB defect sample.
Figure 9
Figure 9
Chip surface defect sample.
Figure 10
Figure 10
Comparison of PCB dataset detection effects.
Figure 10
Figure 10
Comparison of PCB dataset detection effects.
Figure 10
Figure 10
Comparison of PCB dataset detection effects.
Figure 11
Figure 11
Training results of the YOLOv8 algorithm on PCB dataset.
Figure 12
Figure 12
Training results of the RST-YOLOv8 algorithm on PCB dataset.
Figure 13
Figure 13
Training results of the YOLOv8 algorithm on Chip Surface Defect Dataset.
Figure 14
Figure 14
Training results of the RST-YOLOv8 algorithm on Chip Surface Defect Dataset.
Figure 15
Figure 15
Comparison of chip surface defect detection effects.
Figure 16
Figure 16
The network convergence of the RST-YOLOv8 algorithm on the Chip Surface Defect Dataset.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Wang X., Gao S., Guo J., Wang C., Xiong L., Zou Y. Deep Learning-Based Integrated Circuit Surface Defect Detection: Addressing Information Density Imbalance for Industrial Application. Int. J. Comput. Intell. Syst. 2024;17:29. doi: 10.1007/s44196-024-00423-w. - DOI
    1. Wei L., Solihin M.I., Astuti W., Hong L.W., Kit A.C. Surface Defects Detection of Cylindrical High-Precision Industrial Parts Based on Deep Learning Algorithms: A Review. Oper. Res. Forum. 2024;5:58. doi: 10.1007/s43069-024-00337-5. - DOI
    1. Redmon J. You only look once: Unified, real-time object detection; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; Las Vegas, NV, USA. 27–30 June 2016.
    1. Redmon J., Farhadi A. YOLO9000: Better, faster, stronger; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; Honolulu, HI, USA. 21–26 July 2017; pp. 7263–7271.
    1. Farhadi A., Redmon J. Yolov3: An incremental improvement; Proceedings of the Computer Vision and Pattern Recognition; Salt Lake City, UT, USA. 18–22 June 2018; Berlin/Heidelberg, Germany: Springer; 2018. pp. 1–6.

LinkOut - more resources