NORMA eResearch @NCI Library

A Resource efficient Method to Detect Rice Leaf Diseases

Katuru, Jaya Sanjeeth Reddy (2022) A Resource efficient Method to Detect Rice Leaf Diseases. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (2MB) | Preview


Rice leaves related diseases affect many farmers globally, posing a threat to the sustainable production of rice. There are several diseases that affect the rice leaf, including bacterial, viral, and fungal infections. Leaves, nodes, panicles, and collars of flag are affected by the fungus. Depending on the part of affected plant the disease is called as leaf blast or rotten neck. Brown Spot, Leaf Blast and Hispa are some common diseases during the growth of rice. The yeild of rice crops can be decreased by 20 to 100 with the increased diseases in rice.A wide variety of machine learning, deep learning and image processing techniques are currently being developed to detect diseases, though these require a great deal of computational power and are not suitable for mobile devices. The development of machine learning models for mobile devices that have limited space and speed is challenging. This research proposes a method Based on mobile devices that require less resources. My proposed framework uses MobileNet architecture which is a light weight neural network and are created for mobile devices. A combination of multiple datasets with 3,336 images is obtained from kaggle and is used to train the model with 4 classes of rice leaf diseases namely hispa, leaf blast, brownspot and healthy. The MobileNetV3, DenseNet169, and InceptionV3 models are trained using data augmentation and transfer learning. Results of the three models are presented in this paper based on accuracy, loss and size. This research proposes a resource efficient model to implement of mobile devices.

Item Type: Thesis (Masters)
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: 21 Feb 2023 11:14
Last Modified: 02 Mar 2023 09:50

Actions (login required)

View Item View Item