<<<  Back

2022, № 95

UDC: 58.084.1 +51-76+ 632.4
GSNTI: 68.37.05, 28.23.15

Automated diagnostics of barley fungal diseases

The paper presents the results of research conducted during 2019-2021 at the experimental training farm “Kuban” of the Kuban State Agrarian University. Using digital intelligent technologies it is shown that the model developed on the basis of the modern SqueezeNet neural network architecture is able to qualitatively and quickly detect and classify barley fungal diseases, such as dark brown spot, powdery mildew, and dwarf rust. For the proposed algorithm, the values of the main classification quality metrics range from 95% to 98%, which indicates its high generalizing ability and the possibility of its using for accurate, prompt and affordable diagnosis of barley diseases in controlled and field conditions.
Keywords: Barley diseases, diagnostics, computer vision, Squeeze Net, convolutional neural network.
DOI: 10.21515/1999-1703-95-69-72

References:

1. Трубилин, И. Т. Основные морфологические и апробационные признаки сортов и гибридов зерновых, зернобобовых, крупяных и масличных растений / И. Т. Трубилин, Н. Р. Шоков, Ю. П. Косенков, Н. Г. Малюга. - Краснодар: КубГАУ, 2000. - 511 с.
2. FAO. World Food and Agriculture - Statistical Yearbook 2021. Rome. - DOI: https://doi.org/10.4060/cb4477en.
3. Краснодарский край в цифрах - 2020: стат. сб. / Фед. Служба гос. стат. Краснодар, 2021. - 266 с.
4. Репко, Н. В. Селекция озимого ячменя на продуктивность и зимостойкость / Н. В. Репко. - Краснодар, 2009. -146 с.
5. Ариничева, И. В. Распознавание болезней риса с помощью современных методов компьютерного зрения / И. В. Ариничева, И. В. Ари-ничев, С. В. Полянских, Г. В. Волкова // Аграрная наука. - 2021. - № 345 (2). - С. 90-94.
6. Arinichev, I. V. Rice Fungal Diseases Recognition Using Modern Computer Vision Techniques / I. V. Arinichev, S. V. Polyanskikh, G. V. Volkova, I. V. Arinicheva // International Journal of Fuzzy Logic and Intelligent Systems. - 2021. - No. 21(1). - P. 1-11. - http://doi.org/10.5391/ IJFIS.2021.21.1.1.
7. Андриянов, Н. А. Обнаружение объектов на изображении: от критериев Байеса и Неймана-Пирсона к детекторам на базе нейронных сетей EfficientDet / Н. А. Андриянов, В. Е. Дементьев, А. Г. Ташлинский // Компьютерная оптика. - 2022. - Т. 46, № 1. - С. 139-159. - DOI: 10.18287/2412-6179-CO-922.

Authors:

1. Arinicheva Irina Vladimirovna, DSc in Biology, professor, Federal State Budgetary Educational Institution of Higher Education “I.T. Trubilin Kuban State Agrarian University”.
2. Arinichev Igor Vladimirovich, PhD in Economics, associate professor, Federal State Budgetary Educational Institution of Higher Education "Kuban State University".
3. Repko Natal'ya Valentinovna, DSc in Agriculture, professor, Federal State Budgetary Educational Institution of Higher Education “I.T. Trubilin Kuban State Agrarian University”.