2026· Journal of Machine Learning Innovations and Artificial Intelligence Horizons· Vol 01, pp. 58-74· 0 citations
TL;DR
This research contributes a systematic evaluation of transfer learning architectures for precision agriculture, demonstrating that pretrained models can effectively reduce computational complexity while maintaining high diagnostic accuracy.
Abstract
Crop diseases pose a substantial threat to global food security, yet existing detection methods often suffer from delays and labor-intensive processes. We present a comparative analysis of four transfer learning architectures—VGG16, ResNet50, MobileNetV2, and EfficientNetB0—for automated crop disease classification from leaf images. Our framework leverages a supervised deep learning approach trained on approximately 54,000 labeled images from six crop species (tomato, potato, maize, pepper, grapes, and apple) sourced from the PlantVillage database, covering seven major disease categories. All images were preprocessed to 224×224 pixels and augmented with rotation, flipping, zoom, and brightness adjustments. We employed a consistent architecture comprising a pretrained CNN feature extractor, global average pooling, a fully connected dense layer, and a softmax classifier. The Adam optimizer with a learning rate of 0.001 and categorical cross-entropy loss were used over 50 epochs with a batch size of 32. The dataset was split into 70% training, 15% validation, and 15% testing. Among all models, EfficientNetB0 achieved the highest accuracy of 97.3%, with precision, recall, and F1-score of 97.0%, 97.1%, and 97.0% respectively. ResNet50 attained 95.4% accuracy, MobileNetV2 reached 94.1%, and VGG16 yielded 93.2%. Confusion matrix analysis revealed minor misclassifications primarily among visually similar fungal diseases. Training curves demonstrated stable convergence with minimal overfitting. The superior performance of EfficientNetB0 highlights its suitability for real-time agricultural monitoring. This research contributes a systematic evaluation of transfer learning architectures for precision agriculture, demonstrating that pretrained models can effectively reduce computational complexity while maintaining high diagnostic accuracy.
This study presents a novel CNN for multi-class classification of 38 diseases, demonstrating an effective balance between predictive performance and computational efficiency, positioning the model as a promising tool for real-world agricultural deployment.
Background: Plant diseases significantly threaten global food security, reducing potential harvests and sometimes causing total crop failure. Traditional detection methods, which rely on manual inspection and laboratory testing, are time-consuming, costly and prone to human error. Methods: To address these challenges, this study applies transfer learning techniques using deep convolutional neural networks for accurate and efficient plant disease detection. A comparative analysis of nine pretrained models, VGG16, VGG19, ResNet50, ResNet101V2, MobileNetV2, InceptionV3, DenseNet121, InceptionResNetV2 and Xception was conducted on the PlantVillage dataset, focusing on apple, potato and peach leaf images. Result: Results show that DenseNet121 and ResNet101V2 achieved the highest accuracy, particularly for potato leaves with 98.5%, while MobileNetV2 also performed well with up to 99% accuracy for apple and peach leaves. The study demonstrates that transfer learning effectively enhances plant disease classification, enabling faster, more reliable and resource efficient detection for precision agriculture.
Chika K. Gangadharan, P.M. Jasmine, Roshni Alex et al.· Indian Journal of Agricultur...· 0 citations
A modified AlexNet architecture for classifying field-captured tomato leaf images into seven disease categories was developed and generally focused on symptom-bearing leaf regions, whereas target spot was the most difficult category to classify.
Debabrat Bharali, Kanak C. Bora, Rashel Sarkar et al.· Journal of Scientific Resear...· 0 citations
Potato leaf disease poses a significant threat to global food security, causing substantial crop losses that jeopardise agricultural productivity and farmers’ livelihoods worldwide. Existing automated detection frameworks suffer from several persistent limitations, including over-reliance on controlled benchmark datasets, narrow disease class coverage, exclusive use of spatial feature representations, absence of feature selection, and dependence on single-architecture end-to-end pipelines. To address these limitations, this paper proposes ComPo-Net, a novel lightweight ensemble framework that integrates three efficient CNN architectures—ResNet18, ShuffleNet, and MobileNetV2—for nine-class potato leaf disease detection and classification. Deep features are extracted from three intermediate layers of each network, with the Discrete Wavelet Transform applied for dimensionality reduction and cross-network fusion of the higher-dimensional layer features, capturing spectral–spatial information that purely spatial approaches cannot provide, while the remaining layer features are directly concatenated across networks. One-way Analysis of Variance (ANOVA) feature selection is subsequently applied to retain the most statistically significant features from the combined multi-scale, multi-network representation, and seven machine learning classifiers are systematically evaluated to identify the optimal classification strategy. The framework is assessed on a merged dataset of three publicly available benchmarks spanning both controlled and uncontrolled imaging environments, constituting a nine-class evaluation setting not previously addressed at this scale in the literature. ComPo-Net achieves an accuracy of 96.32%, an F1-score of 93.87%, an MCC of 0.9350, and AUC values exceeding 0.993 across all nine classes with Cubic SVM as the best-performing classifier. When compared against methods evaluated on the seven-class uncontrolled-environment dataset—the closest available task setting to ComPo-Net’s nine-class merged benchmark—ComPo-Net surpasses the best-performing comparable method by a margin of 6.45 percentage points, demonstrating the effectiveness of multi-scale ensemble feature extraction combined with spectral–spatial representation and principled feature selection for robust potato leaf disease detection under diverse real-world conditions.
Plant diseases have long been considered a major threat to global food production systems. Therefore, early diagnosis is vital to mitigate the risk of these diseases. This task can be challenging, as the number of harmful diseases is substantial. One technology that has gained widespread interest is artificial intelligence, specifically deep learning, which is used to identify plant diseases using leaf patterns. This paper presents two deep learning models, a custom CNN model and a transfer learning model based on the DenseNet-121 architecture. Experiments were carried out using the PlantCity dataset, which consists of twelve subsets of diverse crop species representing fruits, vegetables, and grains with variations among the subsets, including the number of classes, the subset sizes, class distribution, and visual complexity of disease symptoms. The two models were evaluated using multiple metrics, including accuracy, loss, precision, recall, and F1-score. Explainable AI using the LIME technique was deployed to better interpret the acquired results. Results showed that the developed transfer learning model based on DenseNet-121 had superior performance over the CNN model, with accuracies ranging from 86% to 99% across eleven experimented crops. In order to perform an independent experimental validation for the developed model, future work will focus on constructing a local crop dataset captured from Iraqi fields to evaluate the developed models based on the local environment.
H. Jeiad, S. Samaan, Omar Janeh et al.· Automation· 0 citations
An extensive set of experiments was conducted to evaluate the performance of the proposed model for plant disease detection, and it is demonstrated that the model achieves highly reliable results, with an accuracy of 97.13%.
Hayat Meddeber, M. Meddeber· ITEGAM- Journal of Engineeri...· 0 citations
