Published Paper Details:

In recent years, there has been a growing interest in utilizing machine learning techniques to identify medicinal plants. This paper presents an overview of the methodologies and advancements in the field of medicinal plant identification using machine learning techniques. The process involves feature extraction and classification using supervised learning techniques like Random Forest, Convolutional Neural Networks (CNN), and Deep Learning models. Furthermore, the paper highlights the importance of data augmentation, transfer learning, and model interpretability in improving the accuracy and reliability of medicinal plant identification systems. In addition to identification, our system incorporates a recommendation feature based on cosine similarity, which suggests similar medicinal plants based on textual input or plant properties, aiding users in discovering alternative options with similar therapeutic uses. To enhance accessibility and usability across diverse user groups, a translation module powered by the Google ML Kit Translation formation in multiple languages. Overall, our research demonstrates the feasibility and effectiveness of using machine learning techniques for the automated identification and recommendation of medicinal plants. By combining botanical knowledge with advanced computational methods, we pave the way for efficient, multilingual, and reliable identification systems, thereby encouraging the conservation and sustainable utilization of medicinal plant resources. Lastly, future directions and opportunities for research in this domain are proposed, emphasizing the integration of multi-modal data sources, development of user-friendly applications, and deployment of robust and scalable models for real-world applications in healthcare and conservation. Key Words - Machine Learning Algorithm, CNN, Google ML Kit, Cosine Similarity