LeafScan AI: Dual Self-Attention Residual Network for Plant Disease Detection

• Author(s): Harshitha S; Ishwarya S; Janani I
• Paper ID: 1717330
• Page: 1032-1036
• Published Date: 11-05-2026
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 9 Issue 11 May-2026

Abstract

Agriculture plays a vital role in global food security, yet plant diseases continue to cause significant losses in crop yield and quality. This paper presents LeafScan AI, an intelligent plant disease detection system based on a Dual Self-Attention Residual Network (DSRN). The proposed model integrates deep residual learning with spatial and channel attention mechanisms to enhance feature extraction from plant leaf images. Experimental results demonstrate 93.40% accuracy, 91.20% sensitivity, 94.10% specificity, and 92.85% AUC, outperforming existing CNN-based baselines.

Keywords

Plant Disease Detection, Deep Learning, Residual Network, Self-Attention, Dual Attention Mechanism, Leaf Image Classification, PlantVillage Dataset

Citations

IRE Journals:
Harshitha S, Ishwarya S, Janani I "LeafScan AI: Dual Self-Attention Residual Network for Plant Disease Detection" Iconic Research And Engineering Journals Volume 9 Issue 11 2026 Page 1032-1036 https://doi.org/10.64388/IREV9I11-1717330

IEEE:
Harshitha S, Ishwarya S, Janani I "LeafScan AI: Dual Self-Attention Residual Network for Plant Disease Detection" Iconic Research And Engineering Journals, 9(11) https://doi.org/10.64388/IREV9I11-1717330