%0 Journal Article
%T 改进基于YOLOv8的钢材表面缺陷检测算法
Improvement of the Steel Surface Defect Detection Algorithm Based on YOLOv8
%A 孔灏铮
%J Computer Science and Application
%P 539-547
%@ 2161-881X
%D 2025
%I Hans Publishing
%R 10.12677/csa.2025.155126
%X 为提高钢材表面缺陷小目标检测效率，提出一种改进基于YOLOv8的钢材表面缺陷检测算法。通过添加GAM注意力机制，它通过结合了通道注意力和空间注意力，来增强图像特征的表示能力，有助于提升图像处理任务的性能。同时，为了提高小目标检测准确性和更好的多尺度信息融合，特此在里面引入了P2小目标检测头。在NEU-DET数据集上做消融和对比实验，改进算法与原算法比较，precision提高了2.5个百分点；recall提高了3.3个百分点；mAP@0.5提高了2.1个百分点；mAP@0.5：0.95提高了3.5个百分点。
To enhance the efficiency of small target detection for surface defects on steel, we propose an improved steel surface defect detection algorithm based on YOLOv8. This algorithm incorporates the GAM attention mechanism, which integrates both channel and spatial attention, thereby enhancing the representation capability of image features and contributing to improved performance in image processing tasks. Additionally, to further increase the accuracy of small target detection and facilitate better multi-scale information fusion, we introduce a P2 small target detection layer. We conduct ablation and comparative experiments on the NEU-DET dataset. Compared to the original algorithm, the improved algorithm demonstrates an increase in precision by 2.5 percentage points, recall by 3.3 percentage points, mAP@0.5 by 2.1 percentage points, and mAP@0.5:0.95 by 3.5 percentage points.
%K 钢材表面，
%K 缺陷检测，
%K YOLOv8，
%K GAM注意力机制，
%K P2检测头
Steel Surface
%K Defect Detection
%K YOLOv8
%K GAM Attention Mechanism
%K P2 Detection Head
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=114164