Jul 2026· 2026 International Conference on Emerging Trends in Information, Communication & Systems (ICETICS)· pp. 1-5· 0 citations· 15 references
Abstract
The need to enhance crop yield, mitigate losses and ensure sustainable viticulture requires that grapevine diseases be identified accurately and at an early stage. In this paper, an effective deep learning based grapevine leaf classification framework with a fine-tuned MobileNetV3Large model is proposed. The data set used for the experiment was an image data set of 500 grapevine leaves, which included 5 different categories of Buzgulu, Ala Idris, Nazli, Dimnit, and Ak. Numerous preprocessing techniques have been used on the dataset, such as resizing of the image, image normalization, and data augmentation to improve the robustness and generalization of the model. The method of transfer learning was applied by taking MobileNetV3Large pre-trained on the ImageNet dataset and then training the layers that perform multi-class classification. Finally, the model was tested based on the following performance measures; accuracy, precision, recall, F1 score, and confusion matrix. According to the results obtained from the experiment, the precision rate was 96%, and the recall rates were 100%. The convergence and prevention of overfitting by early stopping is effectively indicated by training and validation performance curves. The results demonstrate the appropriateness of deep learning lightweight structures to real-world farming tasks and verify the possibility of the offered model as a dependable instrument to automatize the classification of grapevine diseases and aid precision farming and sustainable vineyard management.
Background: Groundnut is a vital crop affected by several foliar diseases, such as leaf spot, alternaria, rust and rosette. These diseases can reduce crop quality and yield. Manual identification is time-consuming and may lack accuracy. Deep learning methods offer a reliable alternative for automated disease detection. Methods: This study proposes a fine-tuned InceptionV3 convolutional neural network to classify five groundnut leaf classes. A dataset (Sourced from the Mendeley database) of 1,720 high-resolution images was used. These were collected under natural conditions from fields in Ramchandrapur village, West Bengal, India. Images were resized, normalized and augmented to improve model generalization. Transfer learning was applied using the InceptionV3 base model. A custom classification head was added with dense layers, batch normalization, dropout and L2 regularization. The model was trained with the RMSprop optimizer and evaluated using performance matrices, area under the curve (AUC) and Cohen’s Kappa. Result: The proposed model achieved a test accuracy of 98.26%. The macro average F1-score was 0.9872 and cohen’s kappa reached 0.9762. AUC values were above 0.998 for all classes. The model showed excellent performance, especially for minority classes like rosette and rust. It correctly classified almost all samples, with very few misclassifications. Compared to earlier studies, the model performed competitively and offered high interpretability and efficiency. These results support its use in real-world disease diagnosis in agriculture.
Zhe Li, Xue-Lu Qiu· Legume Research An Internati...· 0 citations
Agricultural productivity and food security are heavily impacted by plant diseases, and thus there is a high demand for accurate and automated plant disease detection that can be achieved by applying deep learning techniques. This research proposes a Multi-Model Ensemble Method Based on Deep Learning for multi-plant disease detection using ResNet50 to improve classification performance across multiple crop varieties. The proposed framework takes five important categories of plants into consideration including tomato, potato, grape, apple and maize, and 10 classes of healthy and diseased plants are generated from the PlantSeg dataset. The Anaconda platform was used along with Python to create a development environment that allows data preprocessing, augmentation, training and testing to be implemented efficiently. The proposed ensemble framework combines the feature extraction power of ResNet50 with several deep learning classifiers so as to obtain a good identification performance at different resolutions and environments. The proposed model performance is tested with the following metrics Accuracy, Precision, Inference Time, and Resolution quality and compared with MobileNetV2, YOLOv8 and the baseline CNN models. Experimental results show that the proposed ensemble ResNet50 framework achieves an accuracy of 98.7% and precision of 98.3%, which is about 6.4%, 4.8%, and 9.2% higher than that of MobileNetV2, YOLOv8, and CNN respectively. Moreover, the proposed method achieves high resolution disease localization capability with an inference time improvement of almost 18% compared with YOLOv8. The proposed system greatly improves the detection accuracy of the early stage and the calculation speed of the system, which is very suitable for smart agriculture applications and real-time monitoring of the health status of crops.
A deep learning-based solution to automate disease detection of groundnut leaf conditions that outperformed existing methods such as ResNet50, CNN with progressive resizing, LeafNet and LeafNet and maintained low training and validation loss throughout training.
Jie-Shin Lin, Y. Tai, Suh-Chen Hsiao et al.· Legume Research An Internati...· 0 citations
This research presents an automated detection method using the Single Shot Detector (SSD) framework, with ResNet-50 as the backbone and a Feature Pyramid Network (FPN) to manage multi-scale feature representations to strengthen plant disease monitoring systems.
Kusworo Adi, A. Setiadi, C. E. Widodo et al.· JOIV: International Journal...· 0 citations
