Effects of Different Pre-Trained Deep Learning Algorithms as Feature Extractor in Tomato Plant Health Classification

Chong, Hou Ming and Yin Yap, Xien and Seng Chia, Kim (2023) Effects of Different Pre-Trained Deep Learning Algorithms as Feature Extractor in Tomato Plant Health Classification. Pattern Recognition and Image Analysis, 33 (1). pp. 12-19. ISSN 1054-6618

Text J16084_6c08d828d34b1a281bdc492009add2c0.pdf Restricted to Registered users only Download (701kB) | Request a copy

Abstract

This is a challenge to identify tomato plant diseases using naked eyes. In implementing an automation plantation system, a plant health classification system is necessary in monitoring the health of the plants. This study proposes a system that can classify tomato plant health into five categories of healthy, early blight, late blight, bacterial spot, and yellow leaf curl virus based on their leaves using deep learning algorithms as feature extractors. Five different pre-trained deep learning algorithms (i.e. Resnet-50, AlexNet, GoogleNet, VGG16, and VGG19) were studied and compared. A Raspberry Pi coupled with a camera was proposed to capture tomato plant leaf image. After that, a support vector machine (SVM) with the extracted features was trained for the plant health classification. The results indicate that SVM coupled with ResNet-50 was the best with averaged training and testing accuracies of 98.26 and 93.33%, respectively

Item Type:	Article
Uncontrolled Keywords:	Plant diseases, tomato, deep learning, pre-trained model, classification
Subjects:	T Technology > T Technology (General)
Divisions:	Faculty of Electrical and Electronic Engineering > FKEE
Depositing User:	Mr. Mohamad Zulkhibri Rahmad
Date Deposited:	03 Sep 2024 08:48
Last Modified:	03 Sep 2024 08:48
URI:	http://eprints.uthm.edu.my/id/eprint/11556

Actions (login required)

View Item