<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE root>
<article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" article-type="research-article" dtd-version="1.2" xml:lang="en"><front><journal-meta><journal-id journal-id-type="publisher-id">Discrete and Continuous Models and Applied Computational Science</journal-id><journal-title-group><journal-title xml:lang="en">Discrete and Continuous Models and Applied Computational Science</journal-title><trans-title-group xml:lang="ru"><trans-title>Discrete and Continuous Models and Applied Computational Science</trans-title></trans-title-group></journal-title-group><issn publication-format="print">2658-4670</issn><issn publication-format="electronic">2658-7149</issn><publisher><publisher-name xml:lang="en">Peoples' Friendship University of Russia named after Patrice Lumumba (RUDN University)</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="publisher-id">47502</article-id><article-id pub-id-type="doi">10.22363/2658-4670-2025-33-4-361-373</article-id><article-id pub-id-type="edn">HYUCMC</article-id><article-categories><subj-group subj-group-type="toc-heading" xml:lang="en"><subject>Computer Science</subject></subj-group><subj-group subj-group-type="toc-heading" xml:lang="ru"><subject>Информатика и вычислительная техника</subject></subj-group><subj-group subj-group-type="article-type"><subject>Research Article</subject></subj-group></article-categories><title-group><article-title xml:lang="en">Leaf disease recognition using deep learning methods</article-title><trans-title-group xml:lang="ru"><trans-title>Распознавание болезней листьев с помощью методов глубокого обучения</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0003-4304-7469</contrib-id><name-alternatives><name xml:lang="en"><surname>Muthana</surname><given-names>Ali  Salem</given-names></name><name xml:lang="ru"><surname>Мутхана</surname><given-names>А. С.</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><bio xml:lang="en"><p>PhD Student </p></bio><email>m2112648@edu.misis.ru</email><xref ref-type="aff" rid="aff1"/></contrib><contrib contrib-type="author"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-3420-3805</contrib-id><name-alternatives><name xml:lang="en"><surname>Lyapuntsova</surname><given-names>Elena V.</given-names></name><name xml:lang="ru"><surname>Ляпунцова</surname><given-names>Е. В.</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><bio xml:lang="en"><p>Professor </p></bio><email>lev77@me.com</email><xref ref-type="aff" rid="aff1"/></contrib></contrib-group><aff-alternatives id="aff1"><aff><institution xml:lang="en">National University of Science and Technology MISIS</institution></aff><aff><institution xml:lang="ru">Национальный исследовательский технологический университет “МИСиС”</institution></aff></aff-alternatives><pub-date date-type="pub" iso-8601-date="2025-12-07" publication-format="electronic"><day>07</day><month>12</month><year>2025</year></pub-date><volume>33</volume><issue>4</issue><issue-title xml:lang="en">VOL 33, No4 (2025)</issue-title><issue-title xml:lang="ru">ТОМ 33, №4 (2025)</issue-title><fpage>361</fpage><lpage>373</lpage><history><date date-type="received" iso-8601-date="2025-12-06"><day>06</day><month>12</month><year>2025</year></date></history><permissions><copyright-statement xml:lang="en">Copyright ©; 2025, Muthana A.S., Lyapuntsova E.V.</copyright-statement><copyright-statement xml:lang="ru">Copyright ©; 2025, Мутхана А.С., Ляпунцова Е.В.</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="en">Muthana A.S., Lyapuntsova E.V.</copyright-holder><copyright-holder xml:lang="ru">Мутхана А.С., Ляпунцова Е.В.</copyright-holder><ali:free_to_read xmlns:ali="http://www.niso.org/schemas/ali/1.0/"/><license><ali:license_ref xmlns:ali="http://www.niso.org/schemas/ali/1.0/">https://creativecommons.org/licenses/by-nc/4.0</ali:license_ref></license></permissions><self-uri xlink:href="https://journals.rudn.ru/miph/article/view/47502">https://journals.rudn.ru/miph/article/view/47502</self-uri><abstract xml:lang="en"><p>The digitalization of crop production has placed leaf-image-based disease recognition among the top research priorities. This paper presents a compact and reproducible system designed for rapid deployment in cloud environments and subsequent adaptation. The proposed approach combines multitask learning (simultaneous prediction of plant species and disease), physiologically motivated channel processing, and error-tolerant data preparation procedures. Experiments were conducted on the New Plant Diseases Dataset (Augmented). To accelerate training, six of the most represented classes were selected, with up to 120 images per class. Images were resized to 192×192 and augmented with geometric and color transformations as well as soft synthetic lesion patches. The ExG greenness index was embedded into the green channel of the input image. The architecture was based on EfficientNet-B0; the proposed HiP²-Net model included two classification heads for disease and species. Training was carried out in two short stages, with partial unfreezing of the base network’s tail in the second stage. Evaluation employed standard metrics, confusion matrices, test-time augmentation, and integrated gradients maps for explainability. On the constructed subset, the multitask HiP²-Net consistently outperformed the frozen baseline model in accuracy and aggregate metrics. Synthetic lesions reduced background sensitivity and improved detection of mild infections, while incorporating ExG enhanced leaf tissue separation under variable lighting. Integrated gradient maps highlighted leaf veins and necrotic spots, strengthening trust in predictions and facilitating expert interpretation. The proposed scheme combines the practicality of cloud deployment with simple, physiology-inspired techniques. Adopting the “species + disease” setup together with ExG preprocessing and soft synthetic lesions improves robustness to lighting, background, and geometric variations, and makes it easier to transfer models to new image collections.</p></abstract><trans-abstract xml:lang="ru"><p>Цифровизация растениеводства выдвинула распознавание болезней по изображениям листьев в число приоритетных задач. В работе представлена компактная и воспроизводимая система, пригодная для быстрого развёртывания в облачной среде и последующей адаптации. Подход сочетает многозадачное обучение (одновременное предсказание вида растения и болезни), физиологически мотивированную обработку каналов и устойчивые к ошибкам процедуры подготовки данных. Эксперименты выполнены на наборе New Plant Diseases Dataset (Augmented). Для ускорения выбраны шесть наиболее представленных классов; по каждому использовано до 120 изображений. Данные масштабировались до 192×192 и дополнялись геометрическими и цветовыми преобразованиями, а также мягкими синтетическими пятнами поражения. Индекс зелени ExG внедрялся в зелёный канал входного изображения. Архитектурной основой служила EfficientNet-B0: предложенная HiP²-Net имела две классификационные головы для болезни и вида. Обучение проводилось в два коротких этапа с частичной разморозкой хвоста базовой сети на втором этапе. Оценивание включало стандартные метрики, матрицы ошибок, тестовую аугментацию при выводе и анализ карт интегрированных градиентов для объяснимости. На сформированном подмножестве многозадачная HiP²-Net стабильно превосходила замороженную базовую модель по доле верных ответов и сводным метрикам. Синтетические пятна снижали чувствительность к фону и помогали распознавать слабые поражения, а внедрение ExG улучшало выделение тканей листа при переменном освещении. Карты интегрированных градиентов показывали фокус на прожилках и очагах некроза, что укрепляло доверие к предсказаниям и облегчало экспертную интерпретацию. Предлагаемая схема соединяет практичность облачного запуска и простые приёмы, опирающиеся на физиологию листа. Рекомендуется использовать постановку «вид+болезнь», включать ExG в предобработку и добавлять мягкие синтетические пятна: эти шаги повышают устойчивость к освещению, фону и геометрическим вариациям и упрощают перенос на новые коллекции изображений.</p></trans-abstract><kwd-group xml:lang="en"><kwd>plant disease recognition</kwd><kwd>leaf images</kwd><kwd>deep learning</kwd><kwd>transfer learning</kwd><kwd>multi-task classification</kwd><kwd>explainability</kwd><kwd>lightweight models</kwd></kwd-group><kwd-group xml:lang="ru"><kwd>распознавание болезней растений</kwd><kwd>изображения листьев</kwd><kwd>глубокое обучение</kwd><kwd>перенос обучения</kwd><kwd>многозадачная классификация</kwd><kwd>интерпретируемость</kwd><kwd>лёгкие модели</kwd></kwd-group><funding-group/></article-meta><fn-group/></front><body></body><back><ref-list><ref id="B1"><label>1.</label><mixed-citation>Chen, R., Qi, H., Liang, Y. &amp; Yang, M. Identification of plant leaf diseases by deep learning based on channel attention and channel pruning. Frontiers in Plant Science 13 (2022).</mixed-citation></ref><ref id="B2"><label>2.</label><mixed-citation>El Fatimi, E. H. Leaf diseases detection using deep learning methods. arXivpreprint. 31 December 2024 (2024).</mixed-citation></ref><ref id="B3"><label>3.</label><mixed-citation>Gupta, A., Garg, P., Thakur, D. &amp; Palit, R. Plant Disease Detection Using Deep Learning in Proceedings of the Fifth Congress on Intelligent Systems (CIS 2024) 1277 (2025), 373–384.</mixed-citation></ref><ref id="B4"><label>4.</label><mixed-citation>Russel, N. S. &amp; Selvaraj, A. Leaf species and disease classification using multiscale parallel deep CNN architecture. Neural Computing and Applications 34, 19217–19237 (2022).</mixed-citation></ref><ref id="B5"><label>5.</label><mixed-citation>Shoaib, M., Shah, B., El-Sappagh, S., Ali, A., et al. An advanced deep learning models-based plant disease detection: A review of recent research. Plant Bioinformatics 14 (2023).</mixed-citation></ref><ref id="B6"><label>6.</label><mixed-citation>Yang, B.,Wang, Z., Guo, J., Guo, L., etal. Identifying plant disease and severity from leaves: A deep multitask learning framework using triple-branch Swin Transformer and deep supervision. Computers and Electronics in Agriculture 209, 107809 (2023).</mixed-citation></ref><ref id="B7"><label>7.</label><mixed-citation>Sundhar, S., Sharma, R., Maheshwari, P., Kumar, S. R. &amp; Kumar, T. S. Enhancing Leaf Disease Classification Using GAT-GCN Hybrid Model. arXiv preprint. 7 April 2025 (2025).</mixed-citation></ref><ref id="B8"><label>8.</label><mixed-citation>Romiyal, G., Selvarajah, T., Roshan, G., Kayathiri, M., et al. Past, present and future of deep plant leaf disease recognition: A survey. Computers and Electronics in Agriculture 234, 110128. doi:10.1016/j.compag.2025.110128 (2025).</mixed-citation></ref><ref id="B9"><label>9.</label><mixed-citation>Tunio, M. H., Li, J., Zeng, X., Ahmed, A., etal. Advancing plant disease classification: A robust and generalized approach with transformer-fused convolution and Wasserstein domain adaptation. Computers and Electronics in Agriculture 226, 109574 (2024).</mixed-citation></ref><ref id="B10"><label>10.</label><mixed-citation>Lu, F., Shangguan, H., Yuan, Y., Yan, Z., et al. LeafConvNeXt: Enhancing plant disease classification for the future of unmanned farming. Computers and Electronics in Agriculture 233, 110165 (2025).</mixed-citation></ref><ref id="B11"><label>11.</label><mixed-citation>Zhang, E., Zhang, N. &amp; Lv, C. A lightweight dual-attention network for tomato leaf disease identification. Frontiers in Plant Science 15, 1420584 (2024).</mixed-citation></ref><ref id="B12"><label>12.</label><mixed-citation>Yao, J., Tran, S. N., Garg, S. &amp; Sawyer, S. Deep Learning for Plant Identification and Disease Classification from Leaf Images: Multi-prediction Approaches. arXiv preprint. 25 October 2023 (2023).</mixed-citation></ref><ref id="B13"><label>13.</label><mixed-citation>Indira, K. &amp; Mallika, H. Classification of Plant Leaf Disease Using Deep Learning. Journal of The Institution of Engineers (India): Series B 105, 609–620 (2024).</mixed-citation></ref><ref id="B14"><label>14.</label><mixed-citation>Deng, H., Luo, D., Zhou, Z., Hou, J., et al. Leaf disease recognition based on channel information attention network. Multimedia Tools and Applications 83, 6601–6619 (2024).</mixed-citation></ref><ref id="B15"><label>15.</label><mixed-citation>Khan, M. A., Huss, Khan, M. S., et al. Deep learning-based segmentation and classification of leaf images for detection of tomato plant disease. Frontiers in Plant Science 13, 1031748 (2022).</mixed-citation></ref><ref id="B16"><label>16.</label><mixed-citation>Chen, W., Chen, J., Duan, R., Fang, Y., et al. MS-DNet: A mobile neural network for plant disease identification. Computers and Electronics in Agriculture 199, 107175 (2022).</mixed-citation></ref><ref id="B17"><label>17.</label><mixed-citation>Quan, S., Wang, J., Jia, Z., Yang, M. &amp; Xu, Q. MS-Net: a novel lightweight and precise model for plant disease identification. Frontiers in Plant Science 14, 1276728 (2023).</mixed-citation></ref><ref id="B18"><label>18.</label><mixed-citation>Shafik, W., Tufail, A., Liyanage, C. D. S. &amp; Apong, R. A. A. H. M. Using transfer learning-based plant disease classification and detection for sustainable agriculture. BMC Plant Biology 24, 136 (2024).</mixed-citation></ref><ref id="B19"><label>19.</label><mixed-citation>Zhang, Z. &amp;Wang, H. MAFDE-DN4: Improved few-shot plant disease classification method based on meta-learning. Computers and Electronics in Agriculture 225, 109540 (2024).</mixed-citation></ref><ref id="B20"><label>20.</label><mixed-citation>Li, H., Zhang, Z., Zhou, P., et al. An Effective Image Classification Method for Plant Diseases with Improved Channel Attention (aECAnet). Symmetry 16, 451 (2024).</mixed-citation></ref><ref id="B21"><label>21.</label><mixed-citation>Zhang, Y., Ren, P., Fu, X., et al. Improving plant disease classification using realistic data augmentation. Multimedia Tools and Applications 83, 37703–37723 (2024).</mixed-citation></ref></ref-list></back></article>
