Objective: To solve the subjectivity and instability of the traditional Baijiu picking method " liquor-receiving according to liquor hop", and the problem that the existing machine vision hops classification method is difficult to meet the real-time classification. Methods: The lightweight YOLOv5 takes YOLOv5s as the initial model, uses the K-mean clustering anchor box to replace the default anchor box to improve the model detection accuracy and stability, uses the shufflenetv2 network to replace the YOLOv5s backbone network for feature extraction, so as to achieve the purpose of lightweight model, and adds the CBAM attention mechanism to make the model pay more attention to the characteristics of hops. Results: Compared with the initial YOLOv5s model, the memory occupied by the lightweight YOLOv5 model is reduced by 92.5%, the parameters are reduced by 93.7%, the calculation is reduced by 63.4%, the detection accuracy is improved by 2.8%, and the FPS is up to 526. Conclusion: The lightweight YOLOv5 reduces the requirements for hardware configuration and can well realize the real-time detection and classification of hops.

Publication Date


First Page


Last Page





[1] 周海燕,张宿义,敖宗华,等.白酒摘酒工艺的研究进展[J].酿酒科技,2015(3):105-107.ZHOU H Y,ZHANG S Y,AO Z H,et al.Research progress in liquor-receiving technology of baijiu(liquor)production[J].Liquor-Making Science & Technology,2015(3):105-107.
[2] 杨静娴,任小洪.基于图像处理的白酒酒花轮廓检测[J].食品与机械,2019,35(12):52-55,145.YANG J X,REN X H.Liquor hop contour detection based on image processing[J].Food & Machinery,2019,35(12):52-55,145.
[3] 余锴鑫.基于图像分类算法的自动化摘酒方法研究[D].杭州:浙江大学,2019:39-51.YU K X.Research on automatic wine picking method based on image classification algorithm[D].Hangzhou:Zhejiang University,2019:39-51.
[4] 杨静娴,任小洪.基于多纹理特征的白酒摘酒酒花图像分类识别[J].包装与食品机械,2021,39(4):38-45.YANG J X,REN X H.Classification and recognition of liquor receiving hops images based on multiple texture feature extraction[J].Packaging and Food Machinery,2021,39(4):38-45.
[5] 潘斌,韩强,姚娅川.基于卷积神经网络的白酒酒花分类研究[J].食品与机械,2021,37(10):30-37,88.PAN B,HAN Q,YAO Y C.Research on classification of liquor hops based on convolution neural network[J].Food & Machinery,2021,37(10):30-37,88.
[6] 何盛国,冯涛,孙毅,等.温度、压力和酒精度控制量质摘酒装置:CN201210569678.2[P].2013-07-31.HE S G,FENG T,SUN Y,et al.Temperature,pressure and alcohol control quality wine picking device:CN201210569678.2[P].2013-07-31.
[7] 赵平.一种自动化操作的白酒量质摘酒装置:CN206188782U[P].2017-05-04.ZHAO P.An automaticbaijiu quality liquor extraction device:CN206188782U[P].2017-05-04.
[8] 孙中理,蔡海燕,刘义会,等.基于量质摘酒工艺的自动化摘酒技术研究[J].酿酒科技,2020(1):17-19,23.SUN Z L,CAI H Y,LIU Y H,et al.Automated liquor-gathering technology based on liquor-gathering according to quality grade[J].Liquor-Making Science & Technology,2020(1):17-19,23.
[9] 黄建勇,吴生文,付建生,等.特香型白酒量质摘酒新工艺的研究及应用[J].中国酿造,2021,40(6):157-161.HUANG J Y,WU S W,FU J S,et al.Research and application of new distillation technology based on liquor quality for te-flavor baijiu[J].China Brewing,2021,40(6):157-161.
[10] 范明明.基于近红外技术的白酒摘酒在线检测装置开发[D].镇江:江苏大学,2019:Ⅰ-Ⅱ.FAN M M.Development of on-line detection device for liquor picking based on near-infrared technology[D].Zhenjiang:Jiangsu University,2019:Ⅰ-Ⅱ.
[11] 何超,余东,李战国,等.近红外光谱技术在量质摘酒中的应用探索[J].酿酒,2019,46(4):58-60.HE C,YU D,LI Z G,et al.Application of near infrared spectroscopyto gathering distillate according to the quality[J].Liquor Making,2019,46(4):58-60.
[12] 周庆伍.白酒近红外在线摘酒技术研究及应用[Z].安徽省,安徽古井贡酒股份有限公司,2018-08-11.ZHOU Q W.Research and application of near infrared on-line wine picking technology for baijiu[Z].Anhui Province,Gujing Group,2018-08-11.
[13] 田子宸.基于计算机视觉的智能摘酒方法研究[D].杭州:浙江大学,2020:15-21.TIAN Z C.Research on intelligent liquor selection method based on computer vision[D].Hangzhou:Zhejiang University,2020:15-21.
[14] 王友战.看酒花接酒在今天的运用[J].酿酒,1993(4):58.WANG Y Z.The use of liquor-receiving according to liquor hops today[J].Liquor Making,1993(4):58.
[15] 王玲敏,段军,辛立伟.引入注意力机制的YOLOv5安全帽佩戴检测方法[J].计算机工程与应用,2022,58(9):203-312.WANG L M,DUAN J,XIN L W.Yolov5 helmet wear detection method with introduction of attention mechanism[J].Computer Engineering and Applications,2022,58(9):203-312.
[16] LIN T Y,DOLLR P,GIRSHICK R,et al.Feature pyramid networks for object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington:IEEE Press,2017:936-944.
[17] LIU S,QI L,QIN H F,et al.Path aggregation network for instance segmentation[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington:IEEE Press,2018:1-9.
[18] MA N N,ZHANG X Y,ZHENG H T,et al.ShuffleNet V2:Practical guidelines for efficient CNN architecture design[J].Computer Science,2018,11 218:122-138.
[19] 李志刚,张娜.一种轻量型YOLOv5交通标志识别方法[J].电讯技术,2022,62(9):1 201-1 206.LI Z G,ZHANG N.A light weight YOLOv5 traffic sign recognition method[J].Telecommunication Engineering,2022,62(9):1 201-1 206.
[20] WOO S,PARK J,LEE J Y,et al.CBAM:Convolutional block attention module[C]//ECCV 2018:Proceedings of the 2018 European Conference on Computer Vision.Cham:Springer,2018:3-19.

Included in

Food Science Commons



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.