Aug 2026· Jurnal Teknik Informatika (Jutif)· 0 citations
TL;DR
The experimental results demonstrate that the transfer learning approach significantly outperformed the custom CNN, with EfficientNet-B0 achieving the highest classification accuracy of 95.73% and improved class separability across disease categories.
Abstract
Tomato leaf diseases pose a serious threat to crop productivity and require accurate and efficient identification methods. Traditional visual inspection is time-consuming and prone to human error, motivating the need for automated image-based classification approaches. This study aims to evaluate the effectiveness of deep learning models for tomato leaf disease classification by comparing a custom Convolutional Neural Network and a transfer learning–based EfficientNet-B0 model. An experimental methodology was employed using a publicly available tomato leaf image dataset comprising nine disease classes and one healthy class. Images were preprocessed and augmented before being used to train a custom CNN and an EfficientNet-B0 model with a two-stage fine-tuning strategy. Model performance was evaluated using accuracy, precision, recall, F1-score, confusion matrices, and Receiver Operating Characteristic–Area Under Curve analysis. The experimental results demonstrate that the transfer learning approach significantly outperformed the custom CNN, with EfficientNet-B0 achieving the highest classification accuracy of 95.73% and improved class separability across disease categories.This research contributes to the field of Informatics and Computer Science by providing empirical evidence on the effectiveness of efficient transfer learning architectures for agricultural image classification. The findings support the development of resource-efficient artificial intelligence systems suitable for smart agriculture and edge-based deployment.
This study applies transfer learning to two CNN architectures, MobileNetV2 and ResNet50, to classify red onion leaf diseases into three classes yellow spot, leaf curl, and healthy leaves, and shows that ResNet50 demonstrates better generalization, with a stable training curve, and outperforms MobileNetV2 in terms of ac...
Results indicate that EfficientNetB0 transfer learning can support accurate, efficient, and practical early detection of grape leaf diseases through a user-accessible web system.
Moh. Ainol Yaqin, Intan Purnama Sari, Olabode D. Ibini· Jurnal Pendidikan Teknologi...· 0 citations
This study improves potato leaf disease detection using a fine-tuned InceptionV3 with data augmentation and dropout, while Grad-CAM visualizations enhance model interpretability, reliability, and practical utility for accurate agricultural disease diagnosis.
Aradhy Tiwari, Amit Saxena, Chandrashekhar Chandrashekhar· Indian Journal of Science an...· 0 citations
A deep learning model designed to automatically detect grape leaf diseases based on images, using a pretrained ResNet50 which is trained on ImageNet as feature extractor and a Convolutional Block Attention Module to boost its discriminative capacity is introduced.
Maajid Bashir, A. Reshi, Shabana Shafi et al.· International Journal of Mac...· 0 citations
Accurate and early detection of citrus leaf diseases is essential for maintaining lemon crop health and yield. This work presents a comparative evaluation of four deep learning architectures — CNN, CNN+LSTM, ResNet50, and DenseNet121 — for multi-class classification of lemon leaf diseases using image-based data. A stan...
K. Ahire· Journal of Intelligent Decis...· 0 citations
This study proposes an integrated hybrid pipeline approach which is the combination of an optimized Inception-v4 Convolutional Neural Network (CNN), YOLOv8 (You Only Look Once version 8) and extreme gradient boosting (XG Boost) models to detect and classify Tomato plant diseases effectively and accurately. The proposed...
S. B., G. S· Journal of Applied Science a...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.