Citation

Uddin, Mohammad Nizam and Sarker, Tushar Chandra and Sefat, Safaitul Islam and Akter, Shamima and Al Farid, Fahmid and Sarker, Md. Tanjil and Abdul Karim, Hezerul and Mansor, Sarina (2024) A Novel Approach for Tomato Leaf Disease Detection and Classification Using Deep Learning. In: 2024 Multimedia University Engineering Conference (MECON), 23-25 July 2024, Cyberjaya, Malaysia.

Text A Novel Approach for Tomato Leaf Disease Detection and Classification Using Deep Learning.pdf - Published Version Restricted to Repository staff only Download (554kB)

Abstract

In the most agriculturally dependent countries both novice and expert observers are appointed to monitor vast agricultural estates. It is vital to have a technique for automatically identifying leaf diseases in order to monitor swiftly and effectively. It is evident that a great deal of research has been done on plant disease using support vector machines, decision trees, or neural networkbased classifiers. The main goal of this study was to develop a tomato leaf disease detection model based on support vector machines (SVM) that could accurately identify and categorize tomato leaf disease with the highest accuracy. Firstly, we incorporate the Hue, Saturation, and Value (HSV) color model to enhance the quality of images. We then remove unwanted noise before cropping and smoothing them, thereby enhancing them for analysis and further processing. In the segmentation stage, we include a threshold value based on the pixel’s properties to divide the image into various portions or areas. After that, in the feature extraction stage, we use the histogram to isolate relevant features. Finally, plant disease detection and classification will be completed by using the SVM model. We collected a tomato Leaf dataset with 25851 images from Kaggle to test and train the proposed model. This procedure will escalate much beyond the scope of the previous research.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Support Vector Machines (SVM), Image Segmentation
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions:	Faculty of Engineering (FOE)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	06 Feb 2025 02:33
Last Modified:	06 Feb 2025 02:33
URII:	http://shdl.mmu.edu.my/id/eprint/13353

Downloads

Edit (login required)