A Novel Feature Extraction Model for the Detection of Plant Disease from Leaf Images in Low Computational Devices

TL;DR

This study targets real-time detection of tomato leaf diseases on low-resource devices by combining a SIFT-driven, patch-based feature extraction pipeline with an evaluation of multiple CNN architectures and the CNN-LBP model. By preprocessing images to isolate disease-relevant leaf regions and focusing on informative patches, the authors compare VGG-16/19, ResNet-50, AlexNet, MobileNet, and CNN-LBP, using ImageNet pretraining and task-specific fine-tuning. AlexNet, when applied to the curated patches, achieves the highest accuracy of 87%, outperforming deeper nets and the lightweight CNN-LBP and MobileNet variants, suggesting strong potential for edge deployment on smartphones. The work highlights a practical path toward edge AI in agriculture and points to future directions in model compression and optimization to further enhance on-device inference efficiency.

Abstract

Diseases in plants cause significant danger to productive and secure agriculture. Plant diseases can be detected early and accurately, reducing crop losses and pesticide use. Traditional methods of plant disease identification, on the other hand, are generally time-consuming and require professional expertise. It would be beneficial to the farmers if they could detect the disease quickly by taking images of the leaf directly. This will be a time-saving process and they can take remedial actions immediately. To achieve this a novel feature extraction approach for detecting tomato plant illnesses from leaf photos using low-cost computing systems such as mobile phones is proposed in this study. The proposed approach integrates various types of Deep Learning techniques to extract robust and discriminative features from leaf images. After the proposed feature extraction comparisons have been made on five cutting-edge deep learning models: AlexNet, ResNet50, VGG16, VGG19, and MobileNet. The dataset contains 10,000 leaf photos from ten classes of tomato illnesses and one class of healthy leaves. Experimental findings demonstrate that AlexNet has an accuracy score of 87%, with the benefit of being quick and lightweight, making it appropriate for use on embedded systems and other low-processing devices like smartphones.

Figures (8)

• Figure 1: The Le-Net CNN model
• Figure 2: Image before preprocessing
• Figure 3: Extraction of important key points from image
• Figure 4: Image with background eliminated
• Figure 5: Training key points of the image after applying SIFT