Ayurvedic Plant Detection With Enhanced Convolutional Neural Networks

Abstract

The field of Ayurvedic medicine heavily relies on the accurate identification of medicinal plants for therapeutic applications. However, manual identification can be time-consuming, error-prone, and dependent on expert knowledge. This paper presents a deep learning-based approach for the detection and classification of Ayurvedic plants to enhance accessibility and reliability in identifying medicinal species. A custom dataset comprising images of various Ayurvedic plants is developed, capturing diverse environmental conditions, angles, and plant features. With the use of a trained deep learning model and the Flask framework for the backend, this application seeks to help botanists, researchers, and enthusiasts identify medicinal plants effectively. A carefully selected dataset was used to train the model, guaranteeing high plant recognition accuracy. Through the program, users can upload photos of plants, and the algorithm uses the inputs to correctly classify the species. This experiment provides a scalable and user-friendly digital solution to the problems associated with manual plant identification. It can be used in the domains of education, agriculture, and medicine, encouraging the study and preservation of ayurvedic plants. The study demonstrates how traditional botany, and artificial intelligence might be combined to meet contemporary demands.