首页|基于改进YOLOv5的卷烟品规智能识别模型研究

基于改进YOLOv5的卷烟品规智能识别模型研究

扫码查看
为实现低成本、便捷、高校的卷烟品规智能识别,降低客户经理盘点库存的时间成本,提升卷烟库存盘点效率,文章在YOLOv5 模型的基础上,引入CA注意力机制,构建一种卷烟品规识别模型.针对卷烟品规识别任务,文章建立了一个多隐含层、多神经元节点的深度学习模型来提取卷烟外观的关键特征,同时实现了对卷烟品规和数量的识别.
Research on intelligent recognition model of cigarette product specifications based on improved YOLOv5
In order to achieve low-cost,convenient and intelligent identification of cigarette specifications in universities,reduce the time cost of customer managers inventorying inventory,and improve the efficiency of cigarette inventory counting,a cigarette specification recognition model is constructed by introducing coordinate attention mechanism on the basis of YOLOv5 model.A deep learning model with multiple hidden layers and multiple neural nodes is established to extract key features of cigarette appearance for the task of cigarette specification recognition,and simultaneously achieve recognition of cigarette specification and quantity.

YOLOv5cigarette product specificationsintelligent recognition

刘晓明、陈皓、王朋波、陶建文、刘艳平

展开 >

陕西省烟草公司商洛分公司,陕西 商洛 726000

商洛市烟草公司商州分公司,陕西 商洛 726000

YOLOv5 卷烟品规 智能识别

中国烟草总公司陕西省公司科技项目专项

SLZY-23-03

2024

无线互联科技
江苏省科学技术情报研究所

无线互联科技

影响因子:0.263
ISSN:1672-6944
年,卷(期):2024.21(8)
  • 6