光学精密工程2024，Vol.32Issue(21)：3222-3230,9.DOI:10.37188/OPE.20243221.3222
基于改进YOLOv8模型的增材制造微小气孔缺陷检测及其尺寸测量
YOLOv8 model-based additive manufacturing micro porosity defect detection and its dimension measurement
摘要
Abstract
To address challenges related to low detection accuracy and poor dimensional measurement preci-sion of small defects on metal additive manufacturing surfaces,this study proposes a novel defect detection method based on the You Only Look Once(YOLO)v8 model.The Efficient Channel Attention(ECA)module is integrated into the detection head of the YOLOv8 framework,and the Complete Intersection Over Union(CIoU)loss function is replaced with the Wise Intersection Over Union(WIoU)loss function,effec-tively mitigating the impact of low-quality samples and enhancing detection performance.To overcome difficul-ties associated with training on high-resolution image datasets,which often lead to overfitting,local features containing target defects are cropped during the training phase to generate the training dataset.During infer-ence,high-resolution test images are divided into smaller sub-images using a sliding window approach for de-fect prediction.Detected defect sub-images are marked as regions of interest,and precise defect size measure-ment is achieved through edge detection techniques in computer vision.Experimental results demonstrate that the improved model achieves a detection accuracy of 94.3%,a recall rate of 93.4%,and an mAP50 of 97.3%,significantly outperforming traditional methods.Furthermore,the dimensional measurement accuracy for small defects reaches 40 μm,highlighting the effectiveness of the proposed approach.关键词
精密测量/计算机视觉/深度学习/缺陷检测/高分辨率图片Key words
precision measurement/computer vision/deep learning/defect detection/high-resolution images分类
信息技术与安全科学引用本文复制引用
蔡引娣,张殿鹏,孙梓盟,王宇轩,朱祥龙,康仁科..基于改进YOLOv8模型的增材制造微小气孔缺陷检测及其尺寸测量[J].光学精密工程,2024,32(21):3222-3230,9.基金项目
国家重点研发计划资助项目(No.2022YFB4600903) （No.2022YFB4600903）
国家自然科学基金联合基金集成项目(No.U23B6005) （No.U23B6005）
中央高校基本科研业务费资助项目(No.DUT24MS005) （No.DUT24MS005）
