用于超纤革表面瑕疵识别的MFL_YOLOv8算法

打开文本图片集

MFL_YOLOv8 algorithm for surface defect detection of microfiberleather

SUN Xiaodong1，ZHU Qibingl*，XUHuawei²，XING Tongzhen 3 ，ZHUHaibin³ （1. School of Internet of Things Engineering， Jiangnan University，Wuxi 214l22，China; 2.Hexin Kuraray Micro Fiber Leather（Jiaxing） Co. ，Ltd，Jiaxing 3l4OO3，China; 3. Zhejiang Maimu Intelligent Technology Co. ，Ltd， Jiaxing 3l4OOO，China） *Corresponding author， E -mail： zhuqib@163.com

Abstract：Microfiber leather is a high-end composite material，and its defect detection is critical for ensur ing product quality.To addressthe challenges posed by the multi-scale，diverse aspect ratios，and numer ous smalldefects on the surface of microfiber leather，the MFL_YOLOv8 algorithm for surface defect detection was proposed in this study. The MFL_YOLOv8 algorithm first introduced the multi-scale feature extraction module DCNv3-LKA based on the Deformable Large Kernel Atention（DLKA） mechanism， which significantly enhanced the backbone network's multi-scale feature extraction capabilities. Subsequently，the incorporation of a P2 feature map and a Dysample upsampling module in the feature pyramid network strengthened the network'sability to extract detail information from small targets.Finally，the Minimum Points Distance Intersection over Union （MPDIoU） was utilized to mitigate the ineficacy of the lossfunction on smalltargets during the initial stages of training，thus improving the detection performance for smalltrgets.Experimental results on a self-constructed microfiber leather surface defect dataset demonstrate that the proposed algorithm achieved 92.47% of average detection precision and 92.40% ofaverage detection recall，with improvements of 5.38% and 7.27% compared to YOLOv8n. Additionally，the algorithm attainsed a frame rate of 135.2 frames per second （FPS），meeting the accuracy and real-time requirements for industrial applications.

Keywords：microfiber leather;defectdetection;DCNv3-LKA；MPDIoU

1引言

超细纤维合成革（简称“超纤革”）是一种结构与性能都酷似天然皮革的新型复合材料，广泛应用于汽车内饰、服装、医疗、军事等领域[1-2]。（剩余14928字）