Medicinal Plants Identification Using Deep Learning

Computer Engineering

Accurately identifying medicinal plants is crucial for their safe and effective use in various fields, including herbal medicine and biodiversity conservation. Manual identification methods are time-consuming, labor-intensive, and prone to errors. Recent advancements in machine learning and computer vision offer a promising solution by automating the identification process through the analysis of leaf images. This research presents a comprehensive study on the identification of various medicinal plants using a range of pre-trained deep learning models. We leverage the Indian medicinal leaves dataset from Kaggle, consisting of 80 species and approximately 6,900 leaf images. After preprocessing the dataset for image size and scaling, we explore multiple pre-trained models, including Xception, ResNet, VGG, and Inception, to evaluate their effectiveness in medicinal plant identification. The experimental results demonstrate the performance of each pre-trained model in accurately predicting the species of medicinal plants from leaf images. Furthermore, we develop a user-friendly interface that allows users to upload leaf images for identification. Upon analysis, the system provides detailed information on the predicted plant name, botanical name, common names, and medicinal uses. The implementation of this project has the potential to significantly benefit various stakeholders, including Ayurvedic practitioners, herbal medicine users, and researchers. By leveraging pre-trained deep learning models, this system streamlines the identification process and facilitates the safe and effective utilization of medicinal plants in healthcare and conservation endeavors.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.