基于深度学习的超市果蔬检索方法

Supermarket Fruit and Vegetable Retrieval Method Based on Deep Learning

针对目前超市果蔬结算方法无法实现类别新增、小样本识别精度低等问题,提出一种基于深度学习的超市果蔬检索方法。该方法通过YOLOv4获取果蔬主体,去除冗余背景信息,同时通过MobileNetV3提取果蔬主体相应的深层语义特征,最后根据度量学习技术完成类别判断。本文在符合超市实际运营情况的条件下进行实验并得出:该方法能够在小样本条件下精确识别不同的果蔬类别,在每类支持集样本数为15时平均识别率达94%左右,时间开销为0.93 s,同时能够实现新类别的实时更新。本文方法极大地降低了传统超市在实际运营中巨大的人力、时间成本,为果蔬零售行业实现智能化、自动化提供了一种解决方案。

In view of the problems that the current settlement method of supermarket fruits and vegetables cannot add new catego⁃ries and low accuracy of small sample recognition,this paper proposes a supermarket fruits and vegetables retrieval method based on deep learning.The method obtains fruit and vegetable subjects through YOLOv4 to remove redundant background infor⁃mation,and extracts corresponding deep semantic features of fruit and vegetable subjects through MobileNetV3.Finally,cat⁃egory judgment is completed according to metric learning technology.This paper conducts experiments in accordance with the ac⁃tual operation conditions of supermarkets and concludes that the method could accurately identify different fruit and vegetable cat⁃egories under the condition of small samples.When the number of samples for each category is 15,the average recognition rate is about 94%,the time cost is 0.93s,and the new categories could be updated in real time.This method greatly reduces the huge la⁃bor and time cost in the actual operation of traditional supermarkets,and provides a solution for the realization of intelligence and automation in the fruit and vegetable retail industry.