NORMA eResearch @NCI Library

Classification of pest-infested citrus leaf images using MobileNet V2 + LSTM based hybrid model

Pal, Aditya Raju (2022) Classification of pest-infested citrus leaf images using MobileNet V2 + LSTM based hybrid model. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (6MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (4MB) | Preview


One of the most important species of plants in the agricultural domain are citrus plants. They have originated in the tropical and subtropical areas of Southeast Asia. It has been observed that there has been a drop in the production of these plants due to rise in plant diseases. It has always been difficult to get a control over the pests in the field of agriculture as most of them travel and infect through the medium of air. The disease they are infected by are in viral or bacterial form. Therefore, there is a need to have a model for accurate and faster detection of these diseases. The solution should be free from having to connect to internet and should be able to use in remote areas. If the disease are identified at an early stage it will help in quicker application of remedial steps which will decrease the crop loss. In this research, we have applied a deep learning approach and used MobileNet V2 + LSTM based hybrid model for classification pest infected leaves and compared its results with MobileNet model. YOLO V5 is also implemented on a small dataset to perform detection of infected area on the leaf. In the past and present, machine learning is used to detect plant leaf infection but it needs connectivity to internet as models demand for high computing power. MoblieNet V2 is a mobile friendly model open sourced by Google to perform ML applications in light weight systems and the implemented hybrid model showed an accuracy of 93.28%.

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
H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Agriculture Industry
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: 27 Feb 2023 16:03
Last Modified: 01 Mar 2023 17:59

Actions (login required)

View Item View Item