基于机器视觉的木质勺子表面缺陷识别方法

打开文本图片集

中图分类号：TP391.4 文献标识码：A 文章编号：2095-2953（2025）02-0018-07

Surface Defect Recognition Method of Wooden Spoon Based on Machine Vision

SUN Si-fan， LI Chun-wei *（College of HomeandArtDesign，NortheastForestry University，Harbin Heilongjiang15OO4O，China）

Abstract：Aiming at the problems such as large amount of labor，low eficiency and insufficient accuracy in manual selection of defective wooden spoons，an improved YOLOv8 based wooden spoon surface defect recognition method was proposed to realize inteligent and automatic surface defect recognition of wooden spoons and improve the efficiency and accuracy of surface defect recognition of wooden spoons.Based on YOLOv8 model，the original feature pyramid is changed into BiFPN repeated bidirectional feature pyramid structure to integrate more features，and the global attention mechanismisadded toNeck tobetercapturethe significantfeatures between theheight，widthand channelof the space.The CIoU lossfunction in the original model isreplaced with SIoUlossfunction.To improve the detection accuracy and training speed.The experimental results show that the mAP of surface defect recognition in the picture of wooden spoon taken by the improved model reaches 91.7% ，which is 3.3% higher than that of the originalYOLOv8 model，superior toother target detection algorithms，andcan provideareference for intelligentand automatic surface defect recognition of wooden spoon.

Key words：wooden spoon;defect recognition; YOLOv8;intelligent木材作为最为关键的战略性资源之一，对我国 经济社会协调发展具有重大作用[1]。（剩余8576字）