Homepage Program Systems: Theory and Applications Русская версия
ISSN 2079-3316 Bilingual online scientific Online scientific journal of the Ailamazyan Program System Institute of the Ailamazyan PSI of PSI of Russian Academy of Science of RAS 12+ 
Volume 16 (2025) . Issue 3 (66) . Paper No. 4 (451)

Artificial intelligence and machine learning

Research Article
DOIDigital Object Identifier 10.25209/2079-3316-2025-16-3-69-97

Identifying healthy and diseased areas of plant leaves using neural networks

Alexander Vladimirovich Smirnov1Correspondent author, Igor Petrovich Tishchenko2

1,2Ailamazyan Program Systems Institute of RAS, Ves'kovo, Russia
1 Alexander Vladimirovich Smirnov — Correspondent author asmirnov_1991@mail.ru

Abstract. This paper presents a study aimed at developing a neural network method for detecting healthy and diseased areas of plant leaves based on their images and calculating the ratio of their areas. The basic network of the FPN architecture with an encoder in the form of the ResNet-34 architecture was used as a neural network model. To train the ANN, binary masks of target areas of plant leaves were used as labels; they were obtained programmatically without manual marking. Due to this, it was possible to achieve a reasonable compromise between the resources required to create masks and their accuracy. When training the neural network model, the accuracy of 96.5% and 78.9% was achieved according to the F1 metric for determining healthy and diseased areas, respectively. Next, the model was inferred, as a result of which the "health" index was calculated for each of the studied leaf images. In the context of the problems being solved, the "health" index is the difference between the percentages of healthy and diseased areas, which can be used to assess the severity of the disease, as well as to monitor the dynamics of the disease as an indicator of the effectiveness of the drugs or care methods used. The scientific novelty of the presented study lies in the creation of a method for automatically determining the ratio of healthy and diseased leaf areas, which combines modern computer vision technologies, machine learning and practical applicability for agronomy and plant growing. (In Russian).

Keywords: neural network analysis, health index, healthy leaf area, diseased leaf area, model

MSC-20202020 Mathematics Subject Classification 68T10; 68T45,68T07MSC-2020 68-XX: Computer science MSC-2020 68Txx: Artificial intelligence MSC-2020 68T10: Pattern recognition, speech recognition MSC-2020 68T45: Machine vision and scene understanding MSC-2020 68T07: Artificial neural networks and deep learning

For citation: Alexander V. Smirnov, Igor P. Tishchenko. Identifying healthy and diseased areas of plant leaves using neural networks. Program Systems: Theory and Applications, 2025, 16:3, pp. 69–97. (In Russ.). https://psta.psiras.ru/2025/3_69-97.

Full text of article (PDF): https://psta.psiras.ru/read/psta2025_3_69-97.pdf.

The article was submitted 30.07.2025; approved after reviewing 07.08.2025; accepted for publication 19.08.2025; published online 25.08.2025.

© Smirnov A. V., Tishchenko I. P.
2025
Editorial address: Ailamazyan Program Systems Institute of the Russian Academy of Sciences, Peter the First Street 4«a», Veskovo village, Pereslavl area, Yaroslavl region, 152021 Russia;   Website:  http://psta.psiras.ru Phone: +7(4852) 695-228;   E-mail: ;   License: CC-BY-4.0License text on the Creative Commons site
© Ailamazyan Program System Institute of Russian Academy of Science (site design) 2010–2025