Medical Plant Species Detection and Usage Suggestion using Neural Networks

Abstract

This research proposes a novel system for identifying medical plant species and suggesting their usage based on image recognition using Convolutional Neural Networks (CNNs). The system aims to bridge the gap between traditional botanical expertise and accessible, reliable information for both medical professionals and the public. We address the challenges of accurate species identification in diverse lighting and environmental conditions, and inaccurate usage suggestions. The system leverages a large, curated dataset of medical plant images and associated usage information. Results demonstrate significantly improved accuracy in species identification and reliable usage recommendations compared to existing methods, offering a valuable tool for healthcare and ethnobotanical research.

Introduction

The accurate identification and safe application of medicinal plants are crucial for traditional and modern medicine. However, misidentification can lead to adverse health effects. Current methods, including reliance on expert knowledge and traditional identification guides, are often time-consuming, require specialized expertise, and lack accessibility for wider use. There is a critical need for a robust, reliable, and user-friendly system that can accurately identify medical plants from images and provide safe usage information. Challenges include the visual similarity between species, variations in plant appearance due to growth stage and environmental factors, and the lack of a comprehensive, easily accessible database of medical plant usage.

Objectives

• Develop a robust deep learning model for accurate medical plant species identification from images.
• Create a comprehensive database of medical plant species and their appropriate usage.
• Design a user-friendly interface for easy plant identification and usage suggestion.