Computer Optics
RUS  ENG    JOURNALS   PEOPLE   ORGANISATIONS   CONFERENCES   SEMINARS   VIDEO LIBRARY   PACKAGE AMSBIB  
General information
Latest issue
Archive

Search papers
Search references

RSS
Latest issue
Current issues
Archive issues
What is RSS



Computer Optics:
Year:
Volume:
Issue:
Page:
Find






Personal entry:
Login:
Password:
Save password
Enter
Forgotten password?
Register


Computer Optics, 2023, Volume 47, Issue 1, Pages 118–125
DOI: https://doi.org/10.18287/2412-6179-CO-1130
(Mi co1109)
 

This article is cited in 6 scientific papers (total in 6 papers)

IMAGE PROCESSING, PATTERN RECOGNITION

Semantic segmentation of rusts and spots of wheat

I. V. Arinicheva, S. V. Polyanskikhb, I. V. Arinichevac

a Kuban State University, Krasnodar
b Plarium, 350059, Krasnodar, Russia, Uralskaya 75/1
c Kuban State Agrarian University
References:
Abstract: The paper explores the possibility of semantic segmentation of the yellow rust and wheat blotch classification using the U-Net convolutional neural network architecture. Based on an own dataset of 268 images, collected in natural conditions and in infectious nurseries of the Federal Research Center for Biological Plant Protection (VNII BZR), it is shown that the U-Net architecture with ResNet decoders is able to qualitatively detect, classify and localize rust and spotting even in cases where diseases are present on the plant at the same time. For individual classes of diseases, the main metrics (accuracy, micro-/macro precision, recall, and F1) range from 0.92 to 0.96. This indicates the possibility of recognizing even a few diseases on a leaf with an accuracy that is not inferior to that of a plant pathology expert. The IoU and Dice segmentation metrics are 0.71 and 0.88, respectively, which indicates a fairly high quality of pixel-by-pixel segmentation and is confirmed by visual analysis. The architecture of the neural network used in this case is quite light-weight, which makes it possible to use it on mobile devices without connecting to the network.
Keywords: semantic segmentation, convolutional neural network, U-Net, wheat diseases, classification of diseases
Funding agency Grant number
Kuban State University МФИ-20.1/121
This work was supported by the Kuban science Foundation (Project No. IFR-20.1/121).
Received: 22.03.2022
Accepted: 16.07.2022
Document Type: Article
Language: Russian
Citation: I. V. Arinichev, S. V. Polyanskikh, I. V. Arinicheva, “Semantic segmentation of rusts and spots of wheat”, Computer Optics, 47:1 (2023), 118–125
Citation in format AMSBIB
\Bibitem{AriPolAri23}
\by I.~V.~Arinichev, S.~V.~Polyanskikh, I.~V.~Arinicheva
\paper Semantic segmentation of rusts and spots of wheat
\jour Computer Optics
\yr 2023
\vol 47
\issue 1
\pages 118--125
\mathnet{http://mi.mathnet.ru/co1109}
\crossref{https://doi.org/10.18287/2412-6179-CO-1130}
Linking options:
  • https://www.mathnet.ru/eng/co1109
  • https://www.mathnet.ru/eng/co/v47/i1/p118
  • This publication is cited in the following 6 articles:
    Citing articles in Google Scholar: Russian citations, English citations
    Related articles in Google Scholar: Russian articles, English articles
    Computer Optics
     
      Contact us:
     Terms of Use  Registration to the website  Logotypes © Steklov Mathematical Institute RAS, 2024