基于深度学习的超市果蔬检索方法

doi:10.3969/j.issn.1006-2475.2024.04.011

摘要/Abstract

摘要： 摘要：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。

关键词: 关键词：图像检索, 果蔬识别, 类别增加, 小样本识别

Abstract:
Abstract: In view of the problems that the current settlement method of supermarket fruits and vegetables cannot add new categories 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 information， and extracts corresponding deep semantic features of fruit and vegetable subjects through MobileNetV3. Finally， category judgment is completed according to metric learning technology. This paper conducts experiments in accordance with the actual operation conditions of supermarkets and concludes that the method could accurately identify different fruit and vegetable categories 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 labor 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.

Key words: Key words: image retrieval, fruit and vegetable recognition, category increase, small sample recognition

中图分类号:

TP391

郭泽昕, 钟国韵, 何剑锋, 张军. 基于深度学习的超市果蔬检索方法[J]. 计算机与现代化, 2024, 0(04): 60-65.

GUO Zexin, ZHONG Guoyun, HE Jianfeng, ZHANG Jun. Supermarket Fruit and Vegetable Retrieval Method Based on Deep Learning[J]. Computer and Modernization, 2024, 0(04): 60-65.

参考文献

［1］卢宏涛，张秦川. 深度卷积神经网络在计算机视觉中的应用研究综述［J］. 数据采集与处理， 2016，31（1）:1-17.
［2］ SHAO W H， LI Y J， DIAO S F， et al. Rapid classification of Chinese quince （Chaenomeles speciosa Nakai） fruit provenance by near-infrared spectroscopy and multivariate calibration［J］. Analytical and Bioanalytical Chemistry， 2017，409:115-120.
［3］ RADI， CIPTOHADIJOYO S， LITANANDA W S， et al. Electronic nose based on partition column integrated with gas sensor for fruit identification and classification［J］. Computers and Electronics in Agriculture， 2016，121:429-435.
［4］ PARDO-MATES N， VERA A， BARBOSA S， et al. Characterization， classification and authentication of fruit-based extracts by means of HPLC-UV chromatographic fingerprints， polyphenolic profiles and chemometric methods［J］. Food Chemistry， 2017，221:29-38.
［5］ BOLLE R M， CONNELL J H， HAAS N， et al. VeggieVision: A produce recognition system［C］// Proceedings of the 3rd IEEE Workshop on Applications of Computer Vision. IEEE， 1996:244-251.
［6］陶华伟，赵力，奚吉，等. 基于颜色及纹理特征的果蔬种类识别方法［J］. 农业工程学报， 2014，30（16）:305-311.
［7］ ZHANG Y D， DONG Z C， CHEN X Q， et al. Image based fruit category classification by 13-layer deep convolutional neural network and data augmentation［J］. Multimedia Tools and Applications， 2019，78（3）:3613-3632.
［8］巨志勇，张泽晨. 一种局部线性编码的深度学习果蔬分类算法［J］. 小型微型计算机系统， 2020，41（4）:741-745.
［9］ KAMILARIS A， PRENAFETA-BOLDU F X. A review of the use of convolutional neural networks in agriculture［J］. The Journal of Agricultural Science， 2018，156（3）:312-322.
［10］ KOROLEV V， MITROFANOV A， KOROTCOV A， et al. Graph convolutional neural networks as "general-purpose" property predictors: The universality and limits of applicability［J］. Journal of Chemical Information and Modeling， 2020，60（1）:22-28.
［11］ GUDIVADA V N， RAGHAVAN V V. Content-based image retrieval systems［J］. Computer， 1995，28（9）:18-22.
［12］黎雯霞，赵智锋，张瑞军，等. 一种智能称重系统的设计与实现［J］. 物流技术， 2015，34（4）:167-169.
［13］ DATTA R， LI J， WANG J Z. Content-based image retrieval: Approaches and trends of the new age［C］// Proceedings of the 7th ACM SIGMM International Workshop on Multimedia Information Retrieval. ACM， 2005:253-262.
［14］ HAMEED K， CHAI D， RASSAU A. A comprehensive review of fruit and vegetable classification techniques［J］. Image and Vision Computing， 2018，80:24-44.
［15］ REN S Q， HE K M， GIRSHICK R， et al. Faster R-CNN: Towards real-time object detection with region proposal networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2017，39（6）:1137-1149.
［16］ BOCHKOVSKIY A， WANG C Y， LIAO H Y M. YOLOv4: Optimal speed and accuracy of object detection［J］. arXiv preprint arXiv:2004.10934， 2020.
［17］ HE K M， ZHANG X Y， REN S Q， et al. Spatial pyramid pooling in deep convolutional networks for visual recognition［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2014，37（9）:1904-1916.
［18］ LIU S， QI L， QIN H F， et al. Path aggregation network for instance segmentation［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE， 2018:8759-8768.
［19］ LUO W J， LI Y J， URTASUN R， et al. Understanding the effective receptive field in deep convolutional neural networks［C］// Proceedings of the 30th International Conference on Neural Information Processing Systems. ACM， 2016:4905-4913.
［20］ NEYSHABUR B， BHOJANAPALLI S， MCALLESTER D， et al. Exploring generalization in deep learning［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. ACM， 2017:5949-5958.
［21］ ZHAO G D， WU Y， CHEN F Q， et al. Effective feature selection using feature vector graph for classification［J］. Neurocomputing， 2015，151:376-389.
［22］ HOWARD A， SANDLER M， CHEN B， et al. Searching for MobileNetV3［C］// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision （ICCV）. IEEE， 2019:1314-1324.
［23］ GUO Y M， LIU Y， OERLEMANS A， et al. Deep learning for visual understanding: A review［J］. Neurocomputing，2016，187:27-48.
［24］ KUMARI A， SHARMA N. A review on convolutional neural networks for skin lesion classification［C］// Proceedings of the 2021 2nd International Conference on Secure Cyber Computing and Communications （ICSCCC）. IEEE， 2021:186-191.
［25］ KAYA M， BILGE H S. Deep metric learning: A survey［J］. Symmetry， 2019，11（9）. DOI: 10.3390/sym11091066.
［26］ XU X Y. Research on the design of the intelligent transportation cycling system based on the Internet of Things technology simulating［C］// Proceedings of the 2016 2nd International Conference on Electronics： Network and Computer Engineering （ICENCE 2016）. Atlantis Press， 2016:66-69.
［27］张万红，朱元骏. 套袋苹果影像的分割方法研究［J］. 北方园艺， 2017（8）:6-9.
［28］苏欣，赖复尧，余容平，等. 基于多视角模板匹配的零件图像检索方法［J］. 机械制造与自动化， 2023，52（1）:222-225.
［29］金柱璋，方旭源，黄彦慧，等. 基于深度度量学习的卫星云图像检索［J］. 光电工程， 2022，49（4）:15-25.
［30］ LIN C H， CHEN R T， CHAN Y K. A smart content-based image retrieval system based on color and texture feature［J］. Image and Vision Computing， 2009，27（6）:658-665.

[1]	郑久超, 赵新元. 基于主题与描述信息的实体链接方法[J]. 计算机与现代化, 2024, 0(12): 10-14.
[2]	张昆1, 张永伟1, 吴永城1, 张笑文2, 翟世臣2. 基于大模型的设备故障知识图谱自动构建方法[J]. 计算机与现代化, 2024, 0(11): 46-53.
[3]	张宇1, 2, 黎靖1, 2, 马铭1, 2, 王众祥1, 2, 孙妍1, 2. YOLOLW:一个新的轻量级目标检测模型[J]. 计算机与现代化, 2024, 0(11): 91-98.
[4]	杜猛俊1, 李昂1, 童俊1, 钱锦1, 康恺1, 王若丁1, 靳文星2. 基于改进极限学习算法的电力信息数据融合模型[J]. 计算机与现代化, 2024, 0(10): 61-64.
[5]	焦一凯1, 2, 朱欣娟1, 2. 公共文化资源标签推荐方法[J]. 计算机与现代化, 2024, 0(10): 107-112.
[6]	杨俞沣1, 2, 夏小云2, 陈泽丰3, 廖伟志2, 李积武2. 融合多策略蜣螂优化算法的外卖订单配送路径优化[J]. 计算机与现代化, 2024, 0(09): 25-32.
[7]	马钰, 杨勇, 任鸽, 帕力旦·吐尔逊. 基于GCN和微调BERT的作文自动评分方法[J]. 计算机与现代化, 2024, 0(09): 33-37.
[8]	刘文亮1, 吴飞1, 何德明1, 赵维伟2, 潘建宏3. 基于相异度矩阵的碎片化回复文本聚类方法[J]. 计算机与现代化, 2024, 0(09): 56-60.
[9]	高猛, 曾宪文. 基于Circle映射和自适应t分布变异改进的鹈鹕优化算法[J]. 计算机与现代化, 2024, 0(09): 69-73.
[10]	余晨曦, 谷林. 基于人体骨架的电梯内异常行为识别预警[J]. 计算机与现代化, 2024, 0(09): 114-120.
[11]	王妍, 丛鑫, 訾玲玲. 结合知识追踪和图卷积的知识概念推荐[J]. 计算机与现代化, 2024, 0(08): 17-23.
[12]	付书岗1, 2, 3. 基于改进YOLOX和新型数据关联方式的无人机#br# 多目标跟踪方法[J]. 计算机与现代化, 2024, 0(08): 59-66.
[13]	魏嘉焜, 王家润. 手势识别与交互综述[J]. 计算机与现代化, 2024, 0(08): 67-76.
[14]	王涛1, 2, 黄丹1, 2, 刘禅奕1, 2, 朱桃1, 2. 基于YOLOv5s的无人机图像车辆检测[J]. 计算机与现代化, 2024, 0(08): 108-113.
[15]	杨江1, 孙晓梅1, 许韬2. 基于业务内容构建股票关联关系的股价预测[J]. 计算机与现代化, 2024, 0(07): 21-25.