Recent Papers

Medicinal plant identification plays a vital role in botany, pharmacology, and healthcare byfacilitating the discovery of plant-based therapeutic solutions. Traditional identificationmethods are time-consuming, prone to errors, and require expert knowledge. This studyproposes an automated approach using machine learning and deep learning techniques toenhance the accuracy and efficiency of medicinal plant classification.The proposed system extracts relevant features from medicinal plant images and stores themin a structured CSV file for further analysis. Two traditional machine learning classifiers,Random Forest (RF) and Support Vector Machine (SVM), are implemented, achievingclassification accuracies of 90.43% and 97.45%, respectively. To improve performance, twodeep learning models, Fully Connected Neural Network (FCNN) and Recurrent NeuralNetwork (RNN), are introduced, both of which attain an accuracy of 95.43%. Feature scalingand label encoding techniques are applied to preprocess the dataset, ensuring optimal modelperformance.The experimental results demonstrate that deep learning models offer competitive accuracyand enhanced feature representation compared to traditional machine learning classifiers.This research underscores the potential of AI-driven plant identification systems torevolutionize medicinal plant classification, providing an efficient and reliable tool forresearchers, herbalists, and healthcare professionals.

Copyright © 2025 Swati Pandey. This is an open access article distributed under the Creative Commons Attribution License.