Plant Leaf Disease Prediction Using Deep Learning

EasyChair Preprint 7569

Abstract

Deep neural networks have proven to be quite effective in picture categorization problems. Here, we demonstrate how neural networks can be used to identify plant infection via picture categorization. We used the Plant leaf dataset, which contains four different types of classes. As a result, the problem we've been dealing with is a multi-class classification problem. As the backbone for our study, we considered three distinct architectures: ResNet50, InceptionV3, and ResNet152V2. On the test set, we discovered that ResNet152v2 produces the best results. We used three measurements to examine the situation: accuracy, review, and the precision disarray metric. We found out that using ResNet152, our model achieves the best results, with an accuracy of 0.984 and a precision of 0.91.

Keyphrases: Deep Neural Networks, NN(Neural Network), multi-class classification

@booklet{EasyChair:7569,
  author    = {Nishaben Sodha and Kunal Chanda and Sanika Rawate and Shivam Chaudhary and Resham Suryawanshi and Neeraj Vazalwar},
  title     = {Plant Leaf Disease Prediction Using Deep Learning},
  howpublished = {EasyChair Preprint 7569},
  year      = {EasyChair, 2022}}