Improved the Notched Character Defect Detection Algorithm of YOLOv8

Hao Jiang; Lu Liu

doi:10.62051/ijcsit.v7n3.01

Authors

Hao Jiang
Lu Liu

DOI:

https://doi.org/10.62051/ijcsit.v7n3.01

Keywords:

Engraved Characters, Defect Detection, YOLOv8, Detection Accuracy

Abstract

Engraved character marking technology is a method of creating permanent identifiers on workpiece surfaces by directly removing material or causing plastic deformation through physical action. This technology is widely used in industrial fields for product traceability, quality control, and anti-counterfeiting certification. However, long-term operation of marking equipment leading to aging and fluctuations in process parameters can easily cause character defects such as broken strokes and distortions, directly affecting the readability and reliability of the identification. This paper addresses the issue of low detection accuracy for common character defects in the original YOLOv8 model by optimizing it. Experiments show that the optimized model significantly improves detection accuracy for various defect types compared to the original model, achieving satisfactory detection performance.

Downloads

Download data is not yet available.

References

[1] Zou Z, Chen K, Shi Z, et al. Object detection in 20 years: A survey [J]. Proceedings of the IEEE, 2023.

[2] Lienhart R, Maydt J. An extended set of haar-like features for rapid object detection [C]//Proceedings. international conference on image processing. IEEE, 2002, 1: I-I

[3] Rätsch G, Onoda T, Müller K R. Soft margins for AdaBoost [J]. Machine learning, 2001, 42: 287-320.

[4] Dalal N, Triggs B. Histograms of oriented gradients for human detection [C]//2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05). Ieee, 2005, 1: 886-893.

[5] Girshick R. Fast R-CNN [C]. International Conference on Computer Vision, 2015:

[6] Cortes C. Support-Vector Networks [J]. Machine Learning, 1995.

[7] Girshick R, Iandola F, Darrell T, et al. Deformable part models are convolutional neural networks [C]//Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 2015: 437-446.

[8] Redmon J, Divvala S, Girshick R, et al. You Only Look Once: Unified, Real-Time Object Detection [C]. IEEE Conference on Computer Vision and Pattern Recognition, 2016: 779-78

[9] Liu W, Anguelov D, Erhan D, et al. SSD: Single Shot MultiBox Detector [C]. European Conference on Computer Vision. Springer International Publishing, 2016: 21-37.

[10] Redmon J, Farhadi A. YOLOv3: An Incremental Improvement [C]. IEEE Conference on Computer Vision and Pattern Recognition, 2018: 1-6.

[11] Alexey Bochkovskiy, Chien-Yao Wang, Hong-Yuan Mark Liao. YOLOv4: Optimal Speed and Accuracy of Object Detection [C]. IEEE Conference on Computer Vision and Pattern Recognition, 2020: 1-6.