Optimization of Mobile Screen Defect Detection Algorithm Based on Lightweight YOLOv8

Hanlin Huang

doi:10.47297/taposatWSP2633-456914.20250610

PDF
导出
分享
收藏
专辑

Optimization of Mobile Screen Defect Detection Algorithm Based on Lightweight YOLOv8

6卷第10期

浏览量: 0 Downloads: 0

Optimization of Mobile Screen Defect Detection Algorithm Based on Lightweight YOLOv8
Optimization of Mobile Screen Defect Detection Algorithm Based on Lightweight YOLOv8
School of Advanced Manufacturing and School of Marine Sciences, Fuzhou University, Quanzhou, Fujian, 362200, China
2025年6卷第10期页码：72-80
纸质出版：2025-10-30
DOI：10.47297/taposatWSP2633-456914.20250610
Accepted：

Scan QR Code

Hanlin Huang. (2025). Optimization of Mobile Screen Defect Detection Algorithm Based on Lightweight YOLOv8. 科技理论与实践（英文版）, 6(10), 72-80.

Huang Hanlin.Optimization of Mobile Screen Defect Detection Algorithm Based on Lightweight YOLOv8[J].Theory and Practice of Science and Technology,2025,06(10):72-80.
Hanlin Huang. (2025). Optimization of Mobile Screen Defect Detection Algorithm Based on Lightweight YOLOv8. 科技理论与实践（英文版）, 6(10), 72-80. DOI： 10.47297/taposatWSP2633-456914.20250610.

Huang Hanlin.Optimization of Mobile Screen Defect Detection Algorithm Based on Lightweight YOLOv8[J].Theory and Practice of Science and Technology,2025,06(10):72-80. DOI： 10.47297/taposatWSP2633-456914.20250610.

摘要

Abstract

With the rapid advancement of smart manufacturing and the consumer electronics industry

the surface quality of smartphone screens has become a critical indicator for evaluating product reliability and user experience. Traditional manual inspection methods struggle to meet the demands for efficiency and consistency in modern production. Consequently

automated visual inspection based on deep learning has emerged as a key development direction for industrial quality control. Addressing the limitations of existing YOLOv8 models in detecting small objects and high computational complexity

this paper proposes an improved algorithm

YOLOv8s-M4SE

which integrates a lightweight backbone network with a channel attention mechanism. Using a publicly available mobile screen defect dataset

we expand the sample distribution through multi-dimensional data augmentation strategies. In terms of network architecture

the original YOLOv8s backbone is replaced with MobileNetV4ConvSmall to reduce computational complexity

while introducing the SE channel attention module to enhance defect feature representation. Experimental results demonstrate that the YOLOv8s-M4SE model achieves an excellent balance between detection accuracy and computational efficiency. It provides a viable solution for applying deep learning in quality inspection for consumer electronics manufacturing.

关键词

Keywords

references

R. Khanam, M. Hussain, R. Hill, and P. Allen, "A Comprehensive Review of Convolutional Neural Networks for Defect Detection in Industrial Applications," in IEEE Access, vol. 12 , pp. 94250 – 94295 , 2024 .

G. Yang, W. Xiong, J. Lei, and K. Yang, "Blade-YOLOv8: Improved YOLOv8 for Wind Turbine Blade Defect Detection," 2024 4th Power System and Green Energy Conference (PSGEC), Shanghai, China, 2024, pp. 209 - 213 .

L.-G. Wu, Z. Zhang, L. Chen, and Q. Zhou, "SSB YOLOv8's Method for Detecting Lump Coal in Mine Conveyors," 2024 43rd Chinese Control Conference (CCC), Kunming, China, 2024, pp. 8798 - 8803 .

H. Liu, R. Hu, H. Dong, and Z. Liu, "SFC-YOLOv8: Enhanced Strip Steel Surface Defect Detection Using Spatial-Frequency Domain-Optimized YOLOv8," in IEEE Transactions on Instrumentation and Measurement, vol. 74 , pp. 1 - 11 , 2025, Art no. 9700111.

C. Kamardi et al., "Classification of Alzheimer's Disease using Random Oversampling and Albumentations on Convolutional Neural Network," 2023 Eighth International Conference on Informatics and Computing (ICIC), Manado, Indonesia, 2023, pp. 1 - 6 .

C. Wang, Z. Zhou, and Z. Chen, "An Enhanced YOLOv4 Model With Self-Dependent Attentive Fusion and Component Randomized Mosaic Augmentation for Metal Surface Defect Detection," in IEEE Access, vol. 10 , pp. 97758 - 97766 , 2022 .

J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," 2016 IEEE Conference on Computer Vision and Pattern Reco gnition (CVPR), Las Vegas, NV, USA, 2016, pp. 779 - 788 .

T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie, "Feature Pyramid Networks for Object Detection," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 2017, pp. 936 - 944 .

S. Liu, L. Qi, H. Qin, J. Shi, and J. Jia, "Path Aggregation Network for Instance Segmentation," 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018, pp. 8759 - 8768 .

H. Li, A. Wu, Z. Jiang, F. Liu, and M. Luo, "Improving Object Detection in YOLOv8n with the C2f-f Module and Multi-Scale Fusion Reconstruction," 2024 IEEE 6th Advanced Information Management, Communications, Electronic and Automation Control Conference (IMCEC), Chongqing, China, 2024, pp. 374 - 379 .

R. Varghese and S. M., "YOLOv8: A Novel Object Detection Algorithm with Enhanced Performance and Robustness," 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS), Chennai, India, 2024, pp. 1 - 6 .

S. Du, B. Zhang, P. Zhang, and P. Xiang, "An Improved Bounding Box Regression Loss Function Based on CIOU Loss for Multi-scale Object Detection," 2021 IEEE 2nd International Conference on Pattern Recognition and Machine Learning (PRML), Chengd u, China, 2021, pp. 92 - 98 .

K. He, X. Zhang, S. Ren, and J. Sun, "Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification," 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 2015, pp. 1026 - 1034 .

Qin, D., Leichner, C., Delakis, M., Fornoni, M., Luo, S., Yang, F., Wang, W., Banbury, C.R., Ye, C., Akin, B., Aggarwal, V., Zhu, T., Moro, D., & Howard, A. (2024). MobileNetV4 - Universal Models for the Mobile Ecosystem. European Conference on Computer Vision.

J. Hu, L. Shen, S. Albanie, G. Sun, and E. Wu, "Squeeze-and-Excitation Networks," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42 , no. 8 , pp. 2011 - 2023 , 1 Aug. 2020.

文章被引用时，请邮件提醒。

Submit

Fatigue Driving Detection Based on Convolutional Neural Network Model Connected to New Energy Vehicles

Related Author

Xiang Li Kunming University of Science and Technology Oxbridge College

Related Institution

Kunming University of Science and Technology Oxbridge College

⁰