Citation

Ayyavu, Shobanadevi and G., Raj Kamal and Sayeed, Md. Shohel and T., Veeramakali (2025) Vellore Spiny Brinjal Leaf Disease Classification. In: 2025 International Conference on Computational Robotics, Testing and Engineering Evaluation, ICCRTEE 2025, 28 - 30 May 2025, Virudhunagar, India.

Text Vellore Spiny Brinjal Leaf Disease Classification.pdf - Published Version Restricted to Repository staff only Download (524kB)

Abstract

The Vellore Spiny Brinjal is a pure line variety selected from the village of Elavambadi in the Vellore district of Tamil Nadu. It may be seen as a high-end product with limited availability, distinct texture, rich flavor, and a significant need for skilled craftsmanship. Since the entire plant is covered with thorns, the farming is done effectively only by the farmers practicing the cultivation for generations. It is discovered to be very resistant to the occurrence of little leaf and moderately resistant to the Tobacco Mosaic Virus (TMV), as well as to fruit and shoot borers. The purpose of the project elaborates on the process of building a deep learning model that will allow anyone to classify a single leaf image as healthy or infected by, facilitating early detection of disease and adopt suitable effective preventive measures. A pre-trained Convolutional Neural Network (CNN) architecture (VGG16) was applied to three varied datasets to perform image classification of single leaf images. The student created a third dataset capturing the single leaf images of healthy and infected plants through field visit. The accuracy obtained was ranging between 0.82 to 0.97 for a similar design of pre-trained CNN architecture when applied to the selected datasets. The results of the study will allow the farmers cultivating the variant (Vellore Spiny Brinjal / VRM-l Mullukathiri / G.I-788) to make use of the model in the form of a mobile based application for classification of healthy and infected singe leaf images by taking necessary steps to eradicate the disease and avoid its spread by timely intervention.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Convolutional neural network
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions:	Faculty of Information Science and Technology (FIST)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	27 Aug 2025 07:04
Last Modified:	29 Aug 2025 10:16
URII:	http://shdl.mmu.edu.my/id/eprint/14494

Downloads

Edit (login required)