Detection method of defective coffee beans based on YOLOv5

Authors

ZHANG Cheng-yao, Faculty of Mechanical and Electrical Engineering, Yunnan Agriculture University, Kunming, Yunnan 650201, China
ZHANG Yan-cheng, Faculty of Mechanical and Electrical Engineering, Yunnan Agriculture University, Kunming, Yunnan 650201, China; The Key Laboratory for Crop Production and Smart Agriculture of Yunnan Province, Kunming, Yunnan 650201, ChinaFollow
ZHANG Yu-qian, Faculty of Mechanical and Electrical Engineering, Yunnan Agriculture University, Kunming, Yunnan 650201, China
ZHAO Yu-qing, Faculty of Mechanical and Electrical Engineering, Yunnan Agriculture University, Kunming, Yunnan 650201, China; The Key Laboratory for Crop Production and Smart Agriculture of Yunnan Province, Kunming, Yunnan 650201, China

Corresponding Author(s)

张艳诚（1972—），男，云南农业大学副教授，硕士生导师，硕士。E-mail：zhyancheng72@163.com

Abstract

Objective: To realize the defect detection of coffee beans. Methods: An improved YOLOv5s network was proposed to embed different attention mechanism modules and activation functions with YOLOv5s as the baseline network. Results: The mean accuracy of the CBAM module and the activation function Hardswish improved by 5.3% and 2.9%, respectively, compared with the baseline network. After 200 iterations of training, the model accuracy was 99.5%, the average accuracy was 97.6%, the recall was 0.98, the recognition rate was 64 amplitude/s, and the model size was 15 M. Conclusion: Compared with Faster RCNN, SSD, YOLOv3, YOLOv4 and YOLOv5s, the test algorithm has higher recognition accuracy, more lightweight model and better recognition effect for coffee defective beans.

Publication Date

4-25-2023

First Page

50

Last Page

56,175

DOI

10.13652/j.spjx.1003.5788.2022.80499

Recommended Citation

Cheng-yao, ZHANG; Yan-cheng, ZHANG; Yu-qian, ZHANG; and Yu-qing, ZHAO (2023) "Detection method of defective coffee beans based on YOLOv5," Food and Machinery: Vol. 39: Iss. 2, Article 8.
DOI: 10.13652/j.spjx.1003.5788.2022.80499
Available at: https://www.ifoodmm.cn/journal/vol39/iss2/8

References

[1] 杨耀源, 王泽霖. 加快提升云南咖啡产业竞争力的思考[J]. 农村工作通讯, 2021（6）: 58-59.
[2] 张方. 云南咖啡产业国际竞争力评价及影响因素研究[D]. 昆明: 云南财经大学, 2020: 1-74.
[3] 李梦丽, 张付杰, 杨薇, 等. 云南小粒咖啡烘焙工艺优化及总糖含量的测定[J]. 食品工业科技, 2019, 40（6）: 186-192.
[4] 赵会杰, 赵璟. 云南小粒咖啡绿色产业竞争力研究[J]. 合作经济与科技, 2017（24）: 48-49.
[5] 王莉. 云南农产品品牌营销研究: 以云南小粒咖啡为例[J]. 中国商论, 2016（19）: 7-8.
[6] 陈科圻, 朱志亮, 邓小明, 等. 多尺度目标检测的深度学习研究综述[J]. 软件学报, 2021, 32（4）: 1 201-1 227.
[7] 朱云, 凌志刚, 张雨强. 机器视觉技术研究进展及展望[J]. 图学学报, 2020, 41（6）: 871-890.
[8] 李旭然, 丁晓红. 机器学习的五大类别及其主要算法综述[J]. 软件导刊, 2019, 18（7）: 4-9.
[9] AKBAR M N, RACHMAWATI E, STHEVANIE F. Visual feature and machine learning approach for Arabica green coffee beans grade determination[C]// 2020 the 6th International Conference on Communication and Information Processing. New York: Association for Computing Machinery, 2020: 97-104.
[10] PINTO C, FURUKAWA J, FUKAI H, et al. Classification of green coffee bean images based on defect types using convolutional neural network （CNN）[C]// 2017 International Conference on Advanced Informatics, Concepts, Theory, and Applications, Denpasar, Indonesia. [S.l.]: IEEE, 2017: 1-5.
[11] 周胜安, 黄耿生, 张译匀, 等. 基于深度学习的水果缺陷实时检测方法[J]. 食品与机械, 2021, 37（11）: 123-129.
[12] 张军锋, 尚展垒. 基于深度学习卷积神经网络的花生籽粒完整性检测[J]. 食品与机械, 2022, 38（5）: 24-29, 36.
[13] 刘新宇, 郝同盟, 张红涛, 等. 基于改进YOLOv3网络的烟梗识别定位方法[J]. 食品与机械, 2022, 38（3）: 103-109.
[14] 李聪, 喻国威, 张原嘉, 等. 基于ResNeXt与迁移学习的干制哈密大枣果梗/花萼及缺陷识别[J]. 食品与机械, 2022, 38（1）: 135-140.
[15] 丁奇安, 刘龙申, 陈佳, 等. 基于Jetson Nano+YOLO v5的哺乳期仔猪目标检测[J]. 农业机械学报, 2022, 53（3）: 277-284.
[16] 刘莫尘, 高甜甜, 马宗旭, 等. 基于MSRCR-YOLOv4-tiny的田间玉米杂草检测模型[J]. 农业机械学报, 2022, 53（2）: 246-255, 335.
[17] 宋怀波, 王云飞, 段援朝, 等. 基于YOLO v5-MDC的重度粘连小麦籽粒检测方法[J]. 农业机械学报, 2022, 53（4）: 245-253.
[18] 奉志强, 谢志军, 包正伟, 等. 基于改进YOLOv5的无人机实时密集小目标检测算法[J/OL]. 航空学报. （2022-05-11） [2022-07-23]. http://kns.cnki.net/kcms/detail/11.1929.V.20220509.2316.010.html.
[19] 胡根生, 吴继甜, 鲍文霞, 等. 基于改进YOLOv5网络的复杂背景图像中茶尺蠖检测[J]. 农业工程学报, 2021, 37（21）: 191-198.
[20] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Unified, real-time object detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 779-788.
[21] REDMON J, FARHADI A. YOLO9000: Better, faster, stronger[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 7 263-7 271.
[22] WOO S, PARK J, LEE J Y, et al.Cbam: Convolutional block attention module[C]// Proceedings of the European Conference on Computer Vision （ECCV）. Cham: Springer, 2018: 3-19.
[23] HOWARD A, SANDLER M, CHU G, et al. Searching for MobileNetV3[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2019: 1 314-1 324.
[24] ZHENG Z, WANG P, REN D, et al. Enhancing geometric factors in model learning and inference for object detection and instance segmentation[J]. IEEE Transactions on Cybernetics, 2021, 52（8）: 8 574-8 586.
[25] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 7 132-7 141.
[26] HOU Q, ZHOU D, FENG J. Coordinate attention for efficient mobile network design[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 13 713-13 722.
[27] WANG Q, WU B, ZHU P, et al. Supplementary material for 'ECA-Net': Efficient channel attention for deep convolutional neural networks[C]// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 13-19.
[28] MA N, ZHANG X, SUN J. Funnel activation for visual recognition[C]// European Conference on Computer Vision. Cham: Springer, 2020: 351-368.