WES-HOA-based ReScaleX-CNN for Plant Leaf Disease Classification
Abstract
Plant leaf disease classification involves identification and classification of different diseases based on indicators of plant leaves, which plays a crucial role in managing crop health. However, classifying plant leaf diseases is challenging due to wide variation in leaf shape, texture, and color, which leads to overlapping symptoms and inaccurate classification. In this research, the Wombat Escape Strategy-Hippopotamus Optimization Algorithm-based Recalibrated Multi-Scale Squeeze and Excitation Convolutional Neural Network (WES-HOA-based ReScaleX-CNN) is proposed to classify plant leaf disease accurately. In HOA, WES is incorporated to select the most appropriate features that enhance global searchability by guiding agents away from local optima. ReScaleX-CNN enhances the model’s ability to concentrate on informative features by emphasizing significant spatial and channel-wise information. The multiscale approach captures disease patterns at various resolutions, leading to robust performance. Hence, the proposed method obtains a high accuracy of 99.92% on PlantVillage dataset in comparison with existing methods, such as DeepPlantNet.
Keywords
Local Optima, PlantVillage, Premature Convergence, Recalibrated Multi-Scale Squeeze and Excitation Convolutional Neural Network, Wombat Escape Strategy Hippopotamus Optimization Algorithm
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
S. Akkalappa, Shivaputra, M. Rathod, D. Gowda and S. Sasi, "WES-HOA-based ReScaleX-CNN for Plant Leaf Disease Classification," in Journal of Communications Software and Systems, vol. 22, no. 4, pp. 561-571, August 2026, doi: 10.24138/jcomss-2025-0194
@article{akkalappa2026basedrescalex,
author = {Akkalappa, Spoorthi Pothaganahalli and Shivaputra and Rathod, Meenakshi Laxman and Gowda, Dinesha Puttaraje and Sasi, Smitha},
title = {{WES-HOA-based ReScaleX-CNN for Plant Leaf Disease Classification}},
journal = {Journal of Communications Software and Systems},
month = aug,
year = {2026},
volume = {22},
number = {4},
pages = {561--571},
doi = {10.24138/jcomss-2025-0194},
url = {https://doi.org/10.24138/jcomss-2025-0194}
}