基于改进YOLOv5的服装logo识别  

THE RECOGNITION OF CLOTHING LOGO BASED ON ENHANCED YOLOV5

作　　者：张震[1] 王晓杰 Zhang Zhen;Wang Xiaojie(College of Electrical Engineering,Zhengzhou University,Zhengzhou 450001,Henan,China)

机构地区：[1]郑州大学电气工程学院,河南郑州450001

出　　处：《计算机应用与软件》2025年第3期162-168,189,共8页Computer Applications and Software

基　　金：河南省重大公益专项(201300311200)。

摘　　要：使用改进的YOLOv5算法应用于常见的服装品牌logo识别,采用加权k-means算法聚类得出9个初始锚框,针对原始YOLOv5的主干网络,增加Transformer自注意力机制和SPPF快速空间金字塔池化。在现有的FlickrSportLogos-10数据集的基础上略作调整,删除低质量图片和相似图片,增加高质量图片进行实验。实验结果表明,改进后的YOLOv5算法的mAP@0.5和mAP@0.5:0.95分别达到90.7%和60.1%,相比原始YOLOv5分别提高了0.033和0.016。In this paper,the enhanced YOLOv5 algorithm is applied to clothing brand logo recognition.We used the weighted k-means algorithm to obtain 9 initial anchor boxes,and transformer self-attention mechanism and SPPF model were added to the original YOLOv5 backbone.We made some adjustments on the base of the existing FlickrSportlogos-10 dataset,such as removing some low quality and similar images and adding some high-quality images.The experimental results show that the mAP@0.5 and mAP@0.5:0.95 of the enhanced YOLOv5 algorithm reach 90.7%and 60.1%,which are 0.033 and 0.016 higher than the original YOLOv5 algorithm respectively.

关 键 词：YOLOv5 加权k-means Transformer注意力 Logo识别 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]