基于改进的YOLOv5s结构的手语识别设计  

Sign Language Recognition Design Based on Improved YOLOv5s

作　　者：潘丽 PAN Li(School of Electrical and Automation,Wuhu Institute of Technology,Wuhu 241000,AnHui,China)

机构地区：[1]芜湖职业技术学院电气与自动化学院,安徽芜湖241000

出　　处：《西昌学院学报（自然科学版）》2024年第2期49-55,61,共8页Journal of Xichang University(Natural Science Edition)

基　　金：安徽省高校自然科学研究重点项目(2023AH052386);芜湖职业技术学院2023年度校级“教学质量与教学改革工程”项目(2023xxkc05、2023sczfk02)。

摘　　要：听力障碍者需要通过手语等方式才能进行沟通交流,但是大部分听力正常的群众不会解读手语。为解决该问题,创建了手语数据集,并提出一种基于YOLOv5改进的手语识别模型。该模型采用轻量级网络结构MobileNetV3替换了YOLOv5目标检测算法的骨干网络,取得了很好的效果。经过测试,改进后的模型在手语识别数据集中检测平均精度均值(mAP)达到98.5%,召回率(Recall)为0.92,F1(F1 score)分数为0.929。研究提出的模型在提高训练速度、减少参数量的同时,提高了手语识别的精度,满足实际检测需求。The hearing impaired people need to communicate through sign language and other means,but most people with normal hearing cannot read sign language.To solve this problem,this project created a sign language dataset and proposed an improved sign language recognition model based on YOLOv5s.This model uses lightweight network structure MobileNetV3 to replace the backbone network of YOLOv5s object detection algorithm,and achieves good results.The tests prove that the improved model achieves 98.5%mean Average Precision(mAP),0.92 Recall and 0.929 F1 score in sign language recognition data set.The model proposed in this study not only improves the training speed and reduces the number of parameters,but also improves the accuracy of sign language recognition and meets the actual detection re-quirements.

关 键 词：YOLOv5 MobileNetV3 手语识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]