Automated seed identification with computer vision: challenges and opportunities

被引:7
|
作者
Zhao, Liang [1 ]
Haque, S. M. Rafizul [1 ]
Wang, Ruojing [1 ]
机构
[1] Canadian Food Inspection Agcy, Saskatoon Lab, Seed Sci & Technol, Saskatoon, SK S7N 4L8, Canada
关键词
artificial intelligence; computer vision; dataset construction; deep learning; image analysis; machine learning; seed identification; seed testing; CONVOLUTIONAL NEURAL-NETWORKS; SPARSE-REPRESENTATION; WEED SEEDS; CLASSIFICATION; RECOGNITION; RICE; QUALITY; GRAINS; IMAGES; LOCALIZATION;
D O I
10.15258/sst.2022.50.1.s.05
中图分类号
S3 [农学(农艺学)];
学科分类号
0901 ;
摘要
Applying advanced technologies such as computer vision is highly desirable in seed testing. Among testing needs, computer vision is a feasible technology for conducting seed and seedling classification used in purity analysis and in germination tests. This review focuses on seed identification that currently encounters extreme challenges due to a shortage of expertise, time-consuming training and operation, and the need for large numbers of reference specimens. The reviewed computer vision techniques and application strategies also apply to other methods in seed testing. The review describes the development of machine learning-based computer vision in automating seed identification and their limitations in feature extraction and accuracy. As a subset of machine learning techniques, deep learning has been applied successfully in many agricultural domains, which presents potential opportunities for its application in seed identification and seed testing. To facilitate application in seed testing, the challenges of deep learning-based computer vision systems are summarised through analysing their application in other agricultural domains. It is recommended to accelerate the application in seed testing by optimising procedures or approaches in image acquisition technologies, dataset construction and model development. A concept flow chart for using computer vision systems is proposed to advance computer-assisted seed identification.
引用
收藏
页码:75 / 102
页数:28
相关论文
共 50 条
  • [1] Toward Automated Vehicle Teleoperation: Vision, Opportunities, and Challenges
    Zhang, Tao
    [J]. IEEE INTERNET OF THINGS JOURNAL, 2020, 7 (12): : 11347 - 11354
  • [2] Automated identification of benthic epifauna with computer vision
    Piechaud, Nils
    Hunt, Christopher
    Culverhouse, Phil F.
    Foster, Nicola L.
    Howell, Kerry L.
    [J]. MARINE ECOLOGY PROGRESS SERIES, 2019, 615 : 15 - 30
  • [3] DiSCount: computer vision for automated quantification of Striga seed germination
    Raul Masteling
    Lodewijk Voorhoeve
    Joris IJsselmuiden
    Francisco Dini-Andreote
    Wietse de Boer
    Jos M. Raaijmakers
    [J]. Plant Methods, 16
  • [4] DiSCount: computer vision for automated quantification of Striga seed germination
    Masteling, Raul
    Voorhoeve, Lodewijk
    IJsselmuiden, Joris
    Dini-Andreote, Francisco
    de Boer, Wietse
    Raaijmakers, Jos M.
    [J]. PLANT METHODS, 2020, 16 (01)
  • [5] Computer vision applications in construction: Current state, opportunities & challenges
    Paneru, Suman
    Jeelani, Idris
    [J]. AUTOMATION IN CONSTRUCTION, 2021, 132
  • [6] Low-Power Computer Vision: Status, Challenges, and Opportunities
    Alyamkin, Sergei
    Ardi, Matthew
    Berg, Alexander C.
    Brighton, Achille
    Chen, Bo
    Chen, Yiran
    Cheng, Hsin-Pai
    Fan, Zichen
    Feng, Chen
    Fu, Bo
    Gauen, Kent
    Goel, Abhinav
    Goncharenko, Alexander
    Guo, Xuyang
    Ha, Soonhoi
    Howard, Andrew
    Hu, Xiao
    Huang, Yuanjun
    Kim, Jaeyoun
    Ko, Jong Gook
    Kondratyev, Alexander
    Lee, Junhyeok
    Lee, Seungjae
    Lee, Suwoong
    Li, Zichao
    Liang, Zhiyu
    Liu, Juzheng
    Liu, Xin
    Lu, Yang
    Lu, Yung-Hsiang
    Malik, Deeptanshu
    Nguyen, Hong Hanh
    Park, Eunbyung
    Repin, Denis
    Shen, Liang
    Sheng, Tao
    Sun, Fei
    Svitov, David
    Thiruvathukal, George K.
    Zhang, Baiwu
    Zhang, Jingchi
    Zhang, Xiaopeng
    Zhuo, Shaojie
    Kang, D.
    [J]. IEEE JOURNAL ON EMERGING AND SELECTED TOPICS IN CIRCUITS AND SYSTEMS, 2019, 9 (02) : 411 - 421
  • [7] Pipe clogging in the fertilizer industry, opportunities and challenges for computer vision
    Dias, Jovania
    Duarte, Marta
    Coch, Victor
    Duarte, Nelson
    Oliveira, Vinicius
    Drews, Paulo
    Botelho, Silva
    [J]. IFAC PAPERSONLINE, 2020, 53 (02): : 12008 - 12013
  • [8] Towards automated computer vision: analysis of the AutoCV challenges 2019?
    Liu, Zhengying
    Xu, Zhen
    Escalera, Sergio
    Guyon, Isabelle
    Jacques Junior, Julio C. S.
    Madadi, Meysam
    Pavao, Adrien
    Treguer, Sebastien
    Tu, Wei-Wei
    [J]. PATTERN RECOGNITION LETTERS, 2020, 135 : 196 - 203
  • [9] Computer vision in automated parking systems: Design, implementation and challenges
    Heimberger, Markus
    Horgan, Jonathan
    Hughes, Ciaran
    McDonald, John
    Yogamani, Senthil
    [J]. IMAGE AND VISION COMPUTING, 2017, 68 : 88 - 101
  • [10] Automated as-built 3D reconstruction of civil infrastructure using computer vision: Achievements, opportunities, and challenges
    Fathi, Habib
    Dai, Fei
    Lourakis, Manolis
    [J]. ADVANCED ENGINEERING INFORMATICS, 2015, 29 (02) : 149 - 161