A Comparative Analysis on Machine Learning Models for Accurate Identification of Medical Plants
Plants are essential for human life. They help people breathe, provide food, clothing, medicine, and fuel, and also safeguard the environment. Plants can be loaded with medicinal properties and possess active substances that can be used for medical purposes. Several beneficial plant species are disappearing as a result of such factors as global warming, increasing population, professional secrecy, insufficient government support for research efforts, and the lack of public understanding of medicinal plants. It takes time to identify medicinal plants, therefore use professionals to assist you. For better benefit to humankind, a new method to identify and classify therapeutic plants must be developed. Because of the advanced technology in our day and age, medicinal plant identification and classification is an important subject of research in the field of image processing. Feature extraction and classification are the most important components in the process of identifying medicinal plants and classifying them. This research examines methods used in identifying and classifying medicinal plants as well as the medicinal properties of plants that have become increasingly relevant in the recent past. There is a vital importance placed on identifying the suitable medicinal plants in the creation of an ayurvedic medication. In order to identify a medicinal plant, look for these three features: leaf form, colour, and texture. From the both sides of the leaf, there are both deterministic and nondeterministic factors that identify the species. In this study, a combination of traits is designed that is said to identify a single tree the most effectively while minimising errors. The database is made up of scanned photos of both the front and back side of ayurvedic medicinal plant leaves, which is an ayurvedic medicinal plant identification database. In leaf identification, rates as high as 99% have been found when tested on a wide range of classifiers. Extending the prior work by using dried leaves and feature vectors results in identification using which identification rates of 94% are possible.
Identification of the correct medicinal plants that goes in to the preparation of a medicine is very important in ayurvedic medicinal industry. The main features required to identify a medicinal plant is its leaf shape, colour and texture. Colour and texture from both sides of the leaf contain deterministic parameters to identify the species. This paper explores feature vectors from both the front and back side of a green leaf along with morphological features to arrive at a unique optimum combination of features that maximizes the identification rate. A database of medicinal plant leaves is created from scanned images of front and back side of leaves of commonly used ayurvedic medicinal plants. The leaves are classified based on the unique feature combination. Identification rates up to 99% have been obtained when tested over a wide spectrum of classifiers. The above work has been extended to include identification by dry leaves and a combination of feature vectors is obtained, using which, identification rates exceeding 94% have been achieved.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Declaro que o presente artigo é original, não tendo sido submetido à publicação em qualquer outro periódico nacional ou internacional, quer seja em parte ou em sua totalidade. Declaro, ainda, que uma vez publicado na Revista GEINTEC, o mesmo jamais será submetido por mim ou por qualquer um dos demais co-autores a qualquer outro periódico. Através deste instrumento, em meu nome e em nome dos demais co-autores, porventura existentes, cedo os direitos autorais do referido artigo à Revista GEINTEC, que está autorizada a publicá-lo em meio impresso, digital, ou outro existente, sem retribuição financeira para os autores. Em virtude de aparecerem nesta revista de acesso público, os artigos são de uso gratuito, com atribuições próprias, em aplicações educacionais e não-comerciais.
Copyright: O termo de originalidade deve ser preenchido e submetido em documentos suplementares. Clique aqui para fazer o downloado do MODELO DO TERMO.