Abstract
Objective: Reduce the manufacturing cost of automated mango grading equipment. Methods: The effects of three commonly detection algorithms for mango defect detection were compared, and a defect detection algorithm based on YOLOv5 for mango surface was proposed for the light weight design to work on mobile devices. Results: Compared with the original algorithm, the experimental algorithm can reduce the number of parameters by 45.9%, the number of floating point operations by 46.7%, and the weight file size by 45.2% under the premise of meeting the requirements for mango surface defect detection. Conclusion: the experimental algorithm effectively reduces the performance requirements for deployment equipment, and has potential value in reducing the manufacturing cost of mango grading detection equipment.
Publication Date
4-25-2023
First Page
91
Last Page
95,240
DOI
10.13652/j.spjx.1003.5788.2022.80522
Recommended Citation
Yan-wen, NIE; Jia-chen, YANG; Hui-xin, WEN; Lu, GAO; and Jian, XU
(2023)
"Light weight detection of mango surface defects based on machine vision,"
Food and Machinery: Vol. 39:
Iss.
3, Article 16.
DOI: 10.13652/j.spjx.1003.5788.2022.80522
Available at:
https://www.ifoodmm.cn/journal/vol39/iss3/16
References
[1] 李日旺, 黄国弟, 苏美花, 等. 我国芒果产业现状与发展策略[J]. 南方农业学报, 2013, 44（5）: 875-878.
[2] 刘静, 黄勇平, 章程辉. 视觉系统开发模块在芒果果面缺陷检测中的应用[J]. 食品与机械, 2009, 25（2）: 82-85.
[3] 张烈平, 曾爱群, 陈婷. 基于计算机视觉和神经网络的芒果检测与等级分类[J]. 农机化研究, 2008（10）: 57-60.
[4] 李国进, 董第永, 陈双. 基于计算机视觉的芒果检测与分级研究[J]. 农机化研究, 2015, 37（10）: 13-18, 23.
[5] SAHU D, POTDAR R M. Defect identification and maturity detection of mango fruits using image analysis[J]. American Journal of Artificial Intelligence, 2017, 1（1）: 5-14.
[6] MIM F S, GALIB S M, HASAN M F, et al. Automatic detection of mango ripening stages: An application of information technology to botany[J]. Scientia Horticulturae, 2018, 237: 156-163.
[7] 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.
[8] FU C Y, LIU W, RANGA A, et al. DSSD: Deconvolutional single shot detector[J/OL]. Computer Science. （2017-01-23） [2022-07-15]. https://doi.org/10.48550/arXiv.1701.06659.
[9] REN S, HE K, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[C]// advances in Neural Information Processing Systems. Cambridge: MIT Press, 2015: 91-99.
[10] 包晓敏, 王思琪.基于深度学习的目标检测算法综述[J]. 传感器与微系统, 2022, 41（4）: 5-9.
[11] HAN K, WANG Y, TIAN Q, et al. Ghostnet: More features from cheap operations[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 1 580-1 589.
[12] ZHANG Y F, REN W, ZHANG Z, et al. Focal and efficient IOU loss for accurate bounding box regression[J/OL]. Computer Science. （2021-01-20） [2022-07-18]. https://doi.org/10.48550/arXiv.2101.08158.
[13] HOU Q, ZHOU D, FENG J. Coordinate attention for efficient mobile network design[J/OL]. Computer Science. （2021-03-04） [2022-07-20]. https://doi.org/10.48550/arXiv.2103.02907.
[14] 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: Institute of Electrical and Electronics Engineering, 2018: 7 132-7 141.