Open Access

ARTICLE

DenseSwinGNNNet: A Novel Deep Learning Framework for Accurate Turmeric Leaf Disease Classification

Seerat Singla¹, Gunjan Shandilya¹, Ayman Altameem², Ruby Pant³, Ajay Kumar⁴, Ateeq Ur Rehman^5,*, Ahmad Almogren^6,*

1 Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, 140401, Punjab, India
2 Department of Computer Science and Engineering, College of Applied Studies, King Saud University, Riyadh, 11543, Saudi Arabia
3 Department of Mechanical Engineering, Uttaranchal University, Dehradun, 248007, Uttarakhand, India
4 Department of Mechanical Engineering, Noida Institute of Engineering and Technology (NIET), Greater Noida, 201306, Uttar Pradesh, India
5 School of Computing, Gachon University, Seongnam-si, 13120, Republic of Korea
6 Department of Computer Science, College of Computer and Information Sciences, King Saud University, Riyadh, 11633, Saudi Arabia

* Corresponding Authors: Ateeq Ur Rehman. Email: ; Ahmad Almogren. Email:

(This article belongs to the Special Issue: Application of Digital Agriculture and Machine Learning Technologies in Crop Production)

Phyton-International Journal of Experimental Botany 2025, 94(12), 4021-4057. https://doi.org/10.32604/phyton.2025.073354

Received 16 September 2025; Accepted 24 November 2025; Issue published 29 December 2025

Abstract

Turmeric Leaf diseases pose a major threat to turmeric cultivation, causing significant yield loss and economic impact. Early and accurate identification of these diseases is essential for effective crop management and timely intervention. This study proposes DenseSwinGNNNet, a hybrid deep learning framework that integrates DenseNet-121, the Swin Transformer, and a Graph Neural Network (GNN) to enhance the classification of turmeric leaf conditions. DenseNet121 extracts discriminative low-level features, the Swin Transformer captures long-range contextual relationships through hierarchical self-attention, and the GNN models inter-feature dependencies to refine the final representation. A total of 4361 images from the Mendeley turmeric leaf dataset were used, categorized into four classes: Aphids Disease, Blotch, Leaf Spot, and Healthy Leaf. The dataset underwent extensive preprocessing, including augmentation, normalization, and resizing, to improve generalization. An 80:10:10 split was applied for training, validation, and testing respectively. Model performance was evaluated using accuracy, precision, recall, F1-score, confusion matrices, and ROC curves. Optimized with the Adam optimizer at the learning rate of 0.0001, DenseSwinGNNNet achieved an overall accuracy of 99.7%, with precision, recall, and F1-scores exceeding 99% across all classes. The ROC curves reported AUC values near 1.0, indicating excellent class separability, while the confusion matrix showed minimal misclassification. Beyond high predictive performance, the framework incorporates considerations for cybersecurity and privacy in data-driven agriculture, supporting secure data handling and robust model deployment. This work contributes a reliable and scalable approach for turmeric leaf disease detection and advances the application of AI-driven precision agriculture.

---

Keywords

---