基于YOLOv5改进算法的印花图案疵点检测  

Printing pattern defect detection based on improved YOLOv5algorithm

作　　者：颜学坤 楚建安[1] Yan Xuekun;Chu Jian′an(School of Electronics and Information,Xi′an Polytechnic University,Xi′an 710699,China)

机构地区：[1]西安工程大学电子信息学院,西安710699

出　　处：《电子测量技术》2022年第4期59-65,共7页Electronic Measurement Technology

摘　　要：针对圆网印花图案疵点检测问题,采用了一种基于YOLOv5改进算法模型来检测印花图案的疵点。根据实际的情况对YOLOv5模型网络结构进行了更改,首先,对YOLOv5网络的骨干部分进行优化改进,引入了注意力机制模块,对输入图片的通道注意力和空间注意分别提取特征。其次,针对印花疵点目标较小的情况对网络的检测层结构进行了修改。实验结果显示,改进的YOLOv5检测算法精确率提升了14.4%,检测速度提升了7.6fps,达到了43.1fps满足实时检测要求。Aiming at the problem of defect detection of circular screen printing pattern,an improved algorithm model based on YOLOv5is used to detect the defect of printing pattern.The network structure of YOLOv5model is changed according to the actual situation.Firstly,the backbone of YOLOv5network is optimized and improved,and the attention mechanism module is introduced to extract the features of channel attention and spatial attention of input pictures respectively.Secondly,aiming at the small target of printing defects,the detection layer structure of the network is modified.The experimental results show that the accuracy of the improved YOLOv5detection algorithm is improved by 14.4%,and the detection speed is also improved,reaching 43.1fps,which meets the requirements of real-time detection.

关 键 词：印花疵点 YOLOv5 注意力机制 

分 类 号：TP38[自动化与计算机技术—计算机系统结构]