Machine Learning-Based Recognition of Indian Medicinal Plants Species Using Handcrafted Features

Recognizing and categorizing Indian medicinal plant species plays a vital role in safeguarding biodiversity and advancing pharmaceutical studies. Traditional manual classification methods take a lot of time and often involve mistakes. This paper introduces a machine learning-driven recognition system that automates the classification of Indian medicinal plants through handcrafted feature extraction methods. The method uses color and texture features to improve classification accuracy by analyzing the surface patterns and structural properties of plant leaves. Four machine learning algorithms classify the extracted features, and their performances are compared. The benchmark dataset includes images of various Indian medicinal plant species, which are processed and segmented before feature extraction. The experimental findings indicate that the Random Forest classifier surpasses other models in terms of accuracy, delivering superior classification performance. This approach offers a cost-effective and efficient solution for identifying plant species, helping botanists and researchers automate the classification of medicinal plants.