Cotton Plant Disease Prediction using Resnet50

Arora, Ria (2022) Cotton Plant Disease Prediction using Resnet50. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (983kB) | Preview
Preview	PDF (Configuration manual) Download (738kB) | Preview

Abstract

Plant diseases have become a major problem and have affected the economy adversely. Deep learning has helped on a large scale in detecting plant infections. Cotton is a widely grown crop and it is very important to detect the disease in it. Transfer learning plays a major role in the detection of infections which helps farmers save their plants from getting destroyed. Transfer learning has been used in this research which uses a previously trained model on a new one. ResNet50 transfer learning model has been chosen and data augmentation and fine-tuning have been performed which improves the performance of transfer learning models. The best part about ResNet50 is that it has over 23 million trainable parameters. One advantage of using the ResNet50 architecture is that it has shown strong performance in a wide range of tasks, including image classification, object detection, and semantic segmentation. This is due to its ability to learn deep, hierarchical representations of data, which allows it to capture complex patterns and features in the input. Google’s Keras is a high- level deep learning API for creating neural networks. It is built in Python and is used to make neural network construction simple. It also allows for the calculation of various backend neural networks. Transfer learning has been proven to be the best method for disease detection. The best results are achieved with the data augmentation in the ratio 1:3 and fine-tuning the model. An accuracy of 96.9% has been achieved.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Nayak, Prashanth UNSPECIFIED
Uncontrolled Keywords:	Deep Learning; Transfer learning; Cotton Disease Detection; ResNet50
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science S Agriculture > SB Plant culture Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	17 May 2023 09:47
Last Modified:	17 May 2023 09:47
URI:	https://norma.ncirl.ie/id/eprint/6563

Actions (login required)

View Item