Leaf Disease Detection using Machine Learning and Deep Learning

Leaf Disease Detection using Machine Learning and Deep Learning

Rutuja Pawar1, Priyanka Bhore2
1T.E. Student, AIDS, Ajeenkya D.Y.Patil School of Engineering, Pune, India

2 T.E .Teacher Guide, AIDS, Ajeenkya D.Y.Patil School of Engineering, Pune, India

---------------------------------------------------------------------***---------------------------------------------------------------------

Abstract - Identification of leaf conditions plays an important part in the profitable success of any country. numerous corridor of the factory can be infected by bacteria, contagions, fungi and other conditions, but then we will concentrate only on the study of splint conditions as exploration. We excavated into this content from 2010 to 2022 and set up that numerous experimenters used multiple images or hyperspectrals to study crop conditions. Machine Learning ( ML) and deep learning( DL) models were used to identify different types of splint conditions. We've developed a set of guidelines to help experimenters in this field. Support Vector Machine( SVM), Random Forest, and Multiple Twin SVM( MTSVM) are popular ML models for foliar complaint vaticination; Convolutional Neural Network( CNN), Visual figure Group( VGG), ResNet( RNet), GoogLeNet, Deep CNN( DCNN), Backpropagation Neural Network( BPNN), DenseNet( DNet), LeafNet( LN) and LeNet, for splint complaint discovery acquainted deep literacy models. Among these deep literacy models, it is clear that models similar as CNN, VGG and ResNet have strong capabilities in contagion discovery. The performance of the algorithm is generally related to the F1 score, perfection, delicacy,etc. measured with. This review will be useful to experimenters in the field and those seeking a good variety of ML and DL- grounded groups for foliar complaint opinion.

Key Words: Machine Learning, Deep Learning, SVM, Convolutional Neural Network, DNet, Deep CNN