Jul 2026· 2026 International Conference on Emerging Trends in Information, Communication & Systems (ICETICS)· pp. 1-5· 0 citations· 15 references
Abstract
To correctly distinguish leaf diseases in eggplant (Solanum melongena), it is very important to improve agricultural production systems for precision. This paper presents a comparative analysis of five pre-trained convolutional neural network models, namely ResNet50, MobileNetV2, GoogLeNet, Xception, and VGG16, for multi-class classification of eggplant leaf diseases. In this work, a composite image dataset was developed by combining images from publicly available Kaggle , Mendeley repositories and local dataset (by collection from fields) to improve data diversity and generalization capability. A structurally optimized VGG16 model was developed to process 128 × 128 pixel images, which aimed to reduce computational complexity with preserved classification accuracy. Under the same training environment, the proposed modification achieved a classification accuracy of 96.5%. In addition to quantitative analysis, interpretability of the model was incorporated using Local Interpretable Model-agnostic Explanations (LIME) to generate localized feature attribution maps, thereby addressing the transparency problem associated with deep neural networks. The experimental results demonstrated that, although ResNet50 achieved the highest overall classification accuracy, the modified VGG16 architecture demonstrated a more balanced performance in terms of computational complexity, latency, and interpretability. Thus, the modified VGG16 is a reasonable candidate for use in real-time resource-constrained agricultural disease diagnostic system applications.
India is one of the biggest producers and exporters of mangoes in the world, yet its cultivation is persistently threatened diseases that reduce yield, fruit quality, and orchard longevity. Traditional disease diagnosis is based on agronomists' hand visual inspection, which is a laborious, subjective, and challenging technique to scale across vast plantations. This research provides a hybrid deep learning system that incorporates AlexNet and ResNet-50 for the automated classification of five commercially relevant mango leaf diseases: Bacterial Canker, Anthracnose, Powdery Mildew, Sooty Mould and Healthy foliage. Through a fused, jointly trained classification head, the suggested architecture combines the deep, residual feature hierarchies of ResNet-50 with the shallow, texture-sensitive representations learned by AlexNet, enabling the network to take advantage of complementary visual cues that neither backbone fully captures on its own. The hybrid model was implemented and trained using MATLAB. The trained model achieved a validation accuracy of 99.47%. Comparative analysis against standalone AlexNet, standalone ResNet-50, and other architectures reported in the recent mango plant-disease literature indicates that the hybrid fusion strategy offers a favourable balance of accuracy and convergence stability.
Ranu Solanki, D. Yadav· International Journal For Mu...· 0 citations
Apple fruit has major significance in the global agricultural economy due to the nutritional value that it provides and its economic benefits. In addition, there are many threats to UK apple production from various diseases, including foliar disease. There are several different methods being developed to diagnose plant disease. To overcome these limitations, this paper proposes an automated system for the identification and classification of diseased regions on apple fruit leaves using the MNTV3-ECOC architecture. The first step in the process is to apply Bilateral Filtering to remove noise from the images while preserving leaf vein edges, and (CLAHE) was used to enhance contrast. Then, a SegNet model was utilized to automatically identify the region(s) affected by disease, and after that, a pre-trained version of the MobileNetV3 model was utilized to extract relevant features. Finally, an Error Correcting Output Codes (ECOC) model was used to classify the type of the disease. An experiment was conducted to test the ability of the proposed model using a publicly available dataset consisting of 13,124 images of apple fruit leaves, each classified into one of four disease types. The proposed model achieved a classification accuracy of 97.80% along with a precision of 97.38%, a sensitivity of 97.25%, a specificity of 97.60%, and an F-score of 97.50%. Thus, based on these findings there is a large potential to combine image analysis with deep learning-based feature extraction and intelligent classification algorithms to achieve an earlier disease diagnosis of apple production.
Joice Augustine, S. Saravanan· VFAST Transactions on Softwa...· 0 citations
Artificial intelligence has become an effective tool for improving agricultural productivity through automated crop disease diagnosis. Brinjal (eggplant) cultivation suffers substantial yield losses from diseases such as Shoot and Fruit Borer, Wet Rot, Fruit Cracking, and Phomopsis Blight, yet reliable field-based diagnostic systems remain limited. To address this challenge, we introduce \textit{BrinjalFruitX}, a real-world dataset comprising 1,823 annotated images collected under natural farming conditions in Bangladesh across four disease classes and one healthy class. We propose an interpretable hybrid feature-enhancement deep ensemble framework that integrates image preprocessing, transfer learning, traditional machine learning, class imbalance mitigation, and explainable artificial intelligence. Three preprocessing techniques, Gaussian, Laplacian, and Unsharp Masking, are systematically evaluated, while deep features extracted using pre-trained VGG and ResNet models are classified by Random Forest, K-Nearest Neighbors, and a classifier-level ensemble. The optimal Unsharp--ResNet--Random Forest configuration achieved 80.0\% accuracy with an F1-score of 87.0\%. ADASYN applied in the deep feature space improved minority-class sensitivity, while Grad-CAM and Grad-CAM++ enhanced model interpretability. The proposed framework provides an effective and transparent solution for practical field-level brinjal disease detection and precision agriculture.
Hasnur Jahan, Abu Kowshir Bitto, Susmoy Biswas et al.· EAI Endorsed Transactions on...· 0 citations
Early detection of chili plant diseases is essential for preventing yield loss, yet practical deployment remains challenging due to inconsistent illumination, leaf orientation variability, and the limited computational capacity of low-cost imaging hardware. This study proposes an integrated detection framework combining an ESP32-CAM acquisition pipeline, MQTT-based transmission, and a Python inference engine running a fine-tuned ResNet-18 model optimized for real-world noise conditions. The research aims to determine whether domain-aligned fine-tuning meaningfully improves generalization performance compared to older non-optimized models under field-like variability. Using a four-day observational design with two leaf subsets, the fine-tuned models consistently outperformed their non-fine-tuned counterparts in overall accuracy, per-class stability, and positional robustness. Real-time deployment using the Telegram Bot API successfully delivered classification results and images with low latency, demonstrating operational feasibility for remote plant health monitoring. These findings indicate that targeted fine-tuning is essential for transforming CNN-based classifiers from laboratory prototypes into stable, field-ready systems capable of supporting early disease detection in resource-constrained agricultural environments. Additionally, due to chili is widely cultivated in agroforestry systems in Indonesia, the proposed early disease detection framework offers substantial benefits for maintaining productivity in heterogeneous microclimatic conditions where manual diagnosis is more difficult.
Zharifah Puspita Candini, Dyah Aruming Tyas, E. Putra· Jurnal Penelitian Hutan Tana...· 0 citations
Phytopathological threats to mango (Mangifera indica L.) cultivation cause severe global agricultural yield
losses, necessitating rapid and accurate diagnostic frameworks. This study presents a highly optimized, end-to-end deep
learning pipeline leveraging transfer learning via the EfficientNet-B0 architecture for multi-class mango leaf disease
classification. The model was trained and rigorously evaluated on the MangoLeafBD dataset, comprising 4,000 balanced
images across eight categorical states (one healthy control and seven distinct fungal and bacterial pathologies) captured
under heterogeneous orchard conditions. Utilizing a stratified 70-15-15 data split, the network achieved exceptional
convergence within 16 epochs. Empirical evaluation on an isolated test set of 600 images yielded an absolute classification
accuracy of 100 percent, with precision, recall, and F1-scores of 1.0 across all classes and zero off-diagonal
misclassifications. Furthermore, the pipeline demonstrated near-zero latency inference on standard edge-computing
hardware. These findings validate the deployment viability of lightweight convolutional neural networks in resourceconstrained agricultural environments, establishing a robust and computationally efficient baseline for automated
precision pathology.
Jodell R. Bulaclac, J. D. Carmen· International Journal of Inn...· 0 citations
Pomegranate is a commercially valuable horticulture crop whose productivity is significantly affected by leaf diseases, particularly Bacterial Blight caused by Xanthomonas axonopodis pv. punicae. Early detection is crucial for preventing widespread infection and minimizing economic losses. Conventional diagnostic methods rely on visual examination by experts, which is subjective, labour-intensive and prone to delays. This paper presents a Convolutional Neural Network (CNN)–based deep learning approach for automated detection of pomegranate leaf diseases from image datasets. The proposed architecture processes raw leaf images, performs feature extraction and classifies them into healthy or diseased categories. Data augmentation, normalization and regularization techniques are applied to enhance model robustness and reduce overfitting. Experimental results demonstrate high classification accuracy and improved precision compared to traditional machine learning models. The trained model is further integrated into a web-based interface for real-time prediction, enabling farmers and agricultural practitioners to upload leaf images using low-cost devices. The system supports rapid decision-making and contributes to precision agriculture by providing a scalable, reliable and automated disease identification solution.
Ashwini S. Patil, S. R. Patil, S.R. Kumbhar· International Journal of Adv...· 0 citations