Plant diseases pose a major threat to global agricultural productivity, causing significant yield losses and compromising fruit quality. Grape and pomegranate crops, in particular, are highly vulnerable to fungal, bacterial, and environmental stresses, which manifest as visible symptoms on leaves and fruits. Traditional disease detection methods rely heavily on manual inspection, expert evaluation, and laboratory testing, which are labor-intensive, time-consuming, and subjective. Recent advancements in artificial intelligence (AI), specifically deep learning, offer powerful alternatives through automated image-based disease diagnosis. Convolutional Neural Networks (CNNs) have demonstrated exceptional capability in extracting hierarchical visual features, detecting subtle lesion patterns, and achieving high-accuracy classification even under complex environmental conditions. This research presents a deep learning–based framework for automated disease detection in grape leaves and pomegranate fruits. The system utilizes optimized CNN architectures designed to extract discriminative features from heterogeneous image datasets, including early blight, downy mildew, powdery mildew, bacterial spots, fruit cracks, wilt, heart rot, and sunburn. The proposed framework integrates preprocessing, augmentation, multi-class classification, and hyperparameter tuning to ensure robust generalization under natural field settings. Performance evaluation includes accuracy, precision, recall, F1-score, confusion matrices, and cross-validation. Experimental results demonstrate that CNN-based systems outperform traditional image-processing techniques and offer reliable early detection capabilities. The study highlights the potential of AI-driven tools to reduce crop losses, optimize pesticide use, enhance decision-making, and support precision agriculture practices. This work contributes a scalable, efficient, and real-time disease detection solution for grape and pomegranate cultivation
Keywords: Deep Learning, Convolutional Neural Networks, Plant Disease Detection, Grape Leaves, Pomegranate Fruits
How to cite this article:Kulkarni M, Desai S, Deep Learning-Based Disease Detection in Grape Leaves and Pomegranate Fruits Using CNN.. .Int J Drug Deliv Technol. 2026;16(1s): 1111-1119;DOI: 10.25258/ijddt.16. 1111-1119