Enhancing crop sustainability: GSEBNet for precise tomato leaf disease classification
4 affiliations
- 1Department of Computer Science, Islamia College University
- 2Quantum Technologies and Advanced Computing Institute, King Abdulaziz City for Science and Technology
- 3Department of Electrical Engineering, College of Engineering, Qassim University
- 4Department of Information Technology, College of Computer, Qassim University
Abstract
Introduction: Plant diseases pose a major threat to food-supply sustainability. Early identification of crop diseases is crucial for agricultural production and crop yield. Classifying tomato leaves helps determine the treatments needed to keep crops healthy. Although many deep learning approaches have been proposed for plant disease classification, most rely on laboratory-captured images and struggle with real-field conditions.
Methods: This study introduces an extensive class-based dataset collected in natural environments, visually distinguishing 13 infectious diseases and healthy tomato leaves. We propose the Gamma-preprocessed Squeeze-Excitation Block Network (GSEBNet), a lightweight CNN architecture that integrates Squeeze-and-Excitation (SE) blocks with carefully configured Mobile Inverted Bottleneck Convolution (MBConv) layers and a domain-specific Gamma-Unsharp Brightness Reduction (GUBR) preprocessing pipeline. The model was trained and evaluated on a combined dataset of field-captured (PlantCity) and laboratory (PlantVillage) images covering 14 classes.
Results: The proposed GSEBNet achieved a test accuracy of 99.48% on the 14-class dataset, with precision, recall, F1-score, and Cohen’s Kappa of 99.49%, 99.49%, 0.99, and 0.9944, respectively.
Discussion: The obtained results are competitive with those reported in previous studies, while acknowledging differences in datasets and experimental settings. The synergistic co-design of GUBR preprocessing with SE-enhanced MBConv layers significantly improves feature discriminability in low-quality field-captured images.
Related
- Where next for the discipline of nematology? Trends and implications for workforce sustainability, disease diagnostics, and biosecurity
- Glycolysis-enhancing α1-adrenergic antagonists have therapeutic potential in Alzheimer’s disease
- Dopamine Agonists in Parkinson's Disease Decouple Risk-Taking from Reward-Paired Cues by Enhancing Risky Choice in Their Absence
- Enhancing foot-and-mouth disease virus thermostability with a VP1 substitution selected by host HSP60 inhibition.
- A lightweight privacy-aware federated vision transformer for tomato leaf disease classification
BibTeX
@article{khan2026enhancing,
title = {{Enhancing crop sustainability: GSEBNet for precise tomato leaf disease classification}},
author = {Muhammad Sheraz Khan and Irshad Ahmad and Kainat Nisa and Faisal Alharbi and Mohammed Aloraini and Shabana Habib and Muhammad Islam},
journal = {Frontiers in Plant Science},
year = {2026},
month = oct,
doi = {10.3389/fpls.2026.1947340},
url = {https://www.frontiersin.org/articles/10.3389/fpls.2026.1947340/full},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Enhancing crop sustainability: GSEBNet for precise tomato leaf disease classification
AU - Muhammad Sheraz Khan
AU - Irshad Ahmad
AU - Kainat Nisa
AU - Faisal Alharbi
AU - Mohammed Aloraini
AU - Shabana Habib
AU - Muhammad Islam
PY - 2026
DA - 2026/10/28
JO - Frontiers in Plant Science
DO - 10.3389/fpls.2026.1947340
UR - https://www.frontiersin.org/articles/10.3389/fpls.2026.1947340/full
AB - Introduction: Plant diseases pose a major threat to food-supply sustainability. Early identification of crop diseases is crucial for agricultural production and crop yield. Classifying tomato leaves helps determine the treatments needed to keep crops healthy. Although many deep learning approaches have been proposed for plant disease classification, most rely on laboratory-captured images and struggle with real-field conditions. Methods: This study introduces an extensive class-based dataset collected in natural environments, visually distinguishing 13 infectious diseases and healthy tomato leaves. We propose the Gamma-preprocessed Squeeze-Excitation Block Network (GSEBNet), a lightweight CNN architecture that integrates Squeeze-and-Excitation (SE) blocks with carefully configured Mobile Inverted Bottleneck Convolution (MBConv) layers and a domain-specific Gamma-Unsharp Brightness Reduction (GUBR) preprocessing pipeline. The model was trained and evaluated on a combined dataset of field-captured (PlantCity) and laboratory (PlantVillage) images covering 14 classes. Results: The proposed GSEBNet achieved a test accuracy of 99.48% on the 14-class dataset, with precision, recall, F1-score, and Cohen’s Kappa of 99.49%, 99.49%, 0.99, and 0.9944, respectively. Discussion: The obtained results are competitive with those reported in previous studies, while acknowledging differences in datasets and experimental settings. The synergistic co-design of GUBR preprocessing with SE-enhanced MBConv layers significantly improves feature discriminability in low-quality field-captured images.
SN - 1664-462X
ER -