Comprehensive Analysis of CNN and YOLOv5 Object Detection Model to Classify Phytomedicine Tree’s Leaf Disease

Abstract

Abstract Phytomedicine is not only known to the poor people of East Bengal and West Bengal as a medicine but also as a beacon of hope for survival in a diseased life. In this approach, Terminalia Arjuna, Lawsonia inermis, Azadirachta indica, and Ocimum tenuiflorum Phytomedicine tree datasets. Terminalia Arjuna mainly protects gastric mucosa from oxidative damage and it makes it strong so that the stomach gets protection against ulcers. It also exhibits strong antibacterial and antimicrobial properties which help to fight against stomach infections like gastric, diarrhea, and dysentery. There are various uses of Lawsonia inermis. It is known as a powerful detoxifier and it helps to prefer healthy gum, and healthy hair and reduces arthritis pain. The flower of Lawsonia inermis can be used for headaches due to the heat of the sun. Neem is known as Phytomedicine for all diseases and the most common diseases are treated with acne, nourishing the skin, treating wounds, use to reduce dandruff and joint pain, etc. Mainly it increases immunity and provides a healthy life. Another famous Phytomedicine known as Ocimum tenuiflorum is used to treat kidney stones, alleviate fever and headaches, provide a healthy heart, healthy eye, healthy oral, and fight against acne, etc. It is also known as a big source of vitamin K. The most famous and fast object detection algorithms as YOLOv5 and Keras pre-trained models as Xception, ResNet152V2, VGG19, and InceptionResNetV2 have been developed to predict disease-affected or disease-free leaves. The implemented approach has gained a height accuracy of 97.00% from Xception and 95% accuracy from YOLOv5.