Title: Cultivating resilience in wheat agriculture: a cutting-edge approach to disease management through high-precision wheat leaf segmentation and cross-dataset analysis

Authors: Sai Ram Paidipati; Sathvik Pothuneedi; Vijaya Nagendra Gandham; Lovish Jain; Sandeep Kumar; Arpit Jain

Addresses: Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Andhra Pradesh, India ' Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Andhra Pradesh, India ' Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Andhra Pradesh, India ' Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Andhra Pradesh, India ' School of Computer Science and Artificial Intelligence, SR University, Warangal, India ' Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Andhra Pradesh, India

Abstract: Efficient detection of diseases in wheat plants is essential for boosting agricultural productivity and ensuring food security. This paper introduces a computer vision-based approach using region of interest (ROI) and bounding box (BB) techniques to automate the identification and localization of disease symptoms on wheat leaves. By employing datasets like LWDCD2020 and Wheat Leaf Dataset, the study demonstrates a robust method for image segmentation, achieving superior accuracy. The proposed system integrates pre-processing, feature extraction, and segmentation to detect diseased areas effectively. Experimental results show the approach delivers 99.78% accuracy and a 99.87% dice coefficient on the LWDCD-2020 dataset, while achieving 99.33% accuracy on the Wheat Leaf dataset. The results confirm the superiority of the method against geometric attacks and other state-of-the-art techniques, ensuring high precision and efficiency in disease detection.

Keywords: wheat plant diseases; computer vision; image segmentation; region of interest; ROI; bounding box; BB; LWDCD2020 dataset; agricultural productivity; food security; precision agriculture; sustainable agriculture.

DOI: 10.1504/IJESMS.2025.148284

International Journal of Engineering Systems Modelling and Simulation, 2025 Vol.16 No.5, pp.281 - 293

Received: 11 Dec 2023
Accepted: 10 Apr 2024
Published online: 01 Sep 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article