Exploring Multi-Stage Deep Convolutional Neural Network for Medicinal Plant Disease Diagnosis

DOI

10.2991/978-94-6463-740-3_9How to use a DOI?

Keywords

Medicinal Plant; Herbs; CNN; Deep Learning

Abstract

Medicinal plants play a crucial role in healthcare, but various diseases often threaten their cultivation. Early and accurate diagnosis of plant diseases is essential for maintaining plant health and ensuring sustainable production. Deep learning has emerged as a powerful tool for automated image-based disease diagnosis in recent years. This study explores using a multi-stage deep convolutional neural network (CNN) for medicinal plant disease diagnosis such as Squeeze-Net, Efficient-Net, and Res-Net50. The proposed framework involves several stages, where each stage performs increasingly complex feature extraction, allowing the model to learn fine-grained patterns associated with different plant diseases. In this study, they collected the data from the Mendeley Medicinal Leaf dataset, which contains 8 classes. They performed the results based on several parameters such as accuracy, precision, recall, and F1-score. By training on a dataset of medicinal plant images exhibiting various diseases, the Res-Net50 demonstrates robust performance, with a high classification accuracy of 98%.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Karan Kumar Singh
AU  - Nikita Gajbhiye
AU  - Gouri Sankar Mishra
PY  - 2025
DA  - 2025/06/25
TI  - Exploring Multi-Stage Deep Convolutional Neural Network for Medicinal Plant Disease Diagnosis
BT  - Proceedings of the 6th International Conference on Deep Learning, Artificial Intelligence and Robotics (ICDLAIR 2024)
PB  - Atlantis Press
SP  - 87
EP  - 101
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-740-3_9
DO  - 10.2991/978-94-6463-740-3_9
ID  - Singh2025
ER  -