SIFT and BRISK Feature Fusion Based Leaf Identification of Medicinal Plants

The advancement in digital image processing and machine learning technologies has paved the way for innovative applications in the field of botany and pharmacology, particularly in the identification and characterization of Medicinal plants. The SIFT and BRISK Feature Fusion based Leaf Identification of Medicinal Plants represents a significant stride in this direction. Utilizing a comprehensive dataset that includes images of various medicinal plants such as Aloe vera, Giloy, Neem and Adulsa, the system emphasizes the analysis of leaf characteristics to facilitate species identification. By employing techniques to extract shape features and texture features information from the images, the system demonstrates high precision, recall, and accuracy rates in plant identification. Through the integration of advanced imaging technologies and machine learning algorithms, specifically the use of a Support Vector Machine for classifying plants based on leaf traits, the research introduces a novel method for the effective categorization of the Philippines' diverse flora. Furthermore, the development of a web-based application prototype evaluates the model's practicality in real-world scenarios, offering a reliable tool for healthcare professionals and researchers in identifying complex medicinal plants. This approach, which combines computer vision with machine learning techniques to analyze leaf image features, represents a comprehensive solution to the challenge of species differentiation in the vast and varied world of medicinal plants.