Classification of Medical Plants Based on Hybridization of Machine Learning Algorithms
M. Srinivasa Rao, Santosh Kumar, Konda Srinivasa Rao
Abstract
India is a nation where plants with significant medicinal value cover more than 37% of its land. Every plant is treated as having certain medicinal values, whether it be the roots, trunk, fruits, or leaves. Medical plants help in most of the treatments for human diseases if the plant species are identified more clearly. However, it is difficult for individuals to recognize the medical value of the plant accurately. In this work, we suggest a Hybrid model that overcomes this challenge by fusing together two types of classifiers to accurately identify medicinal plants. These classifiers include Support Vector Machines (SVMs) and Convolutional Neural Networks (CNNs). The proposed system has many advantages. The features are first extracted using a Convolutional Neural Network (CNN), and then the recognizer is a Support Vector Machine (SVM). It ensures that the proposed model automatically recognizes the features in the raw leaves and carries out classification using those features. The classifier has been applied to 72 different medical plant leaves and is above 97%. The results showcase that the proposed method is more advantageous than the single classifier for effectively recognizing medical plants.