Experimental Evaluation of Deep Learning Based Plant Leaf Disease Detection System Using Computer Assisted Image Processing Techniques

P. Ramya, Mohanraj S., Mageshwaran N., Mohamed Shafeeq J., Monishwar D. K.

2025

Abstract

One of the most important contemporary agricultural techniques, plant disease detection aids in the early diagnosis of crop illnesses, which allows for more effective management and the prevention of substantial losses. Color changes, spots, lesions, or structural malformations are common visible indicators of plants damaged by diseases. Handheld, drone-mounted, or integrated into smart agricultural automation systems, high-resolution cameras or sensors record these symptoms. Computer Vision and Deep Learning (ML) algorithms examine the gathered data for patterns in form, texture, and color to determine the presence of illnesses. To achieve accurate disease identification in plant leaves, this paper proposes a novel deep learning model which is Enhanced Neural Classification Network (ENCN). So, the performance of the model can be tested by cross-validating it with a conventional learning scheme Support Vector Machine (SVM). An accurate diagnosis enables farmers to implement timely countermeasures against diseases such as blast, bacterial blight or powdery mildew. The system in many cases will recommend the use of pesticides, changes to that amount of water or fertilizer that is applied to crops or quarantining sick plants to stop disease from spreading, she said. The technology improves productivity, ensures accuracy, reduces costs, and promotes sustainable farming practices by utilizing the resources that are already there more effectively. Recent advancements in plant disease detection including integration of the internet of things and drone monitoring result into crop management, high yield and sustainable agriculture environment. Beyond aiding early diagnosis and management, predictive analysis from plant disease detection systems, based on patterns in historical and environmental data, enables farmers to prepare for future crop disease outbreaks. For all, these systems make it possible to monitor a vast area, which saves time and effort when evaluating the health of enormous farmlands.

Paper Citation

in Harvard Style

Ramya P., S. M., N. M., J. M. and K. M. (2025). Experimental Evaluation of Deep Learning Based Plant Leaf Disease Detection System Using Computer Assisted Image Processing Techniques. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - Volume 1: ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 443-452. DOI: 10.5220/0013867400004919

in Bibtex Style

@conference{icrdicct`2525,
author={P. Ramya and Mohanraj S. and Mageshwaran N. and Mohamed Shafeeq J. and Monishwar D. K.},
title={Experimental Evaluation of Deep Learning Based Plant Leaf Disease Detection System Using Computer Assisted Image Processing Techniques},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - Volume 1: ICRDICCT`25},
year={2025},
pages={443-452},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013867400004919},
isbn={978-989-758-777-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - Volume 1: ICRDICCT`25
TI - Experimental Evaluation of Deep Learning Based Plant Leaf Disease Detection System Using Computer Assisted Image Processing Techniques
SN - 978-989-758-777-1
AU - Ramya P.
AU - S. M.
AU - N. M.
AU - J. M.
AU - K. M.
PY - 2025
SP - 443
EP - 452
DO - 10.5220/0013867400004919
PB - SciTePress