Open AccessFactors influencing the use of Deep Learning for Medicinal Plants Recognition
Author(s) -
J. V. Anchitaalagammai,
J S Shantha Lakshmi Revathy,
S Kavitha,
S. Murali
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2089/1/012055
Subject(s) - jatropha curcas , identification (biology) , medicinal plants , plant identification , artificial intelligence , deep learning , computer science , plant species , traditional medicine , pattern recognition (psychology) , machine learning , botany , biology , medicine
Medicinal plants are very essential in maintaining the physical and mental health of human beings. For providing better treatment, Identification and classification of medicinal plants is essential. In this research paper, main objective is to create a medicinal plant identification system using Deep Learning concept. This system identifies and classifies the medicinal plant species with high accuracy. In this system, five different Indian medicinal plant species namely Pungai, Jamun (Naval), Jatropha curcas, kuppaimeni and Basil are used for identification and classification. The dataset contains 58,280 images, includes approximately 10,000 images for each species. The leaf texture, shape, color, physiological or morphological as the features set for leaf identification. The CNN architecture is used to train the collected dataset and develop the system with high accuracy. As result of this model, 96.67% success rate in finding the corresponding medicinal plant. This model is advisable to use as early detection tool for finding the medicinal plant because of its best success rate