Pomegranate is an economically and nutritionally significant fruit crop whose yield and quality are severely affected by diseases such as bacterial blight, anthracnose, fruit rot, and leaf spot. Early and accurate detection of these diseases is critical to minimizing crop losses and ensuring sustainable agricultural productivity. Conventional manual inspection methods are time-consuming and prone to error, highlighting the need for an automated solution. This study presents an automated pomegranate disease detection system based on image processing and machine learning. The proposed system integrates K-means clustering-based segmentation for isolating infected regions, followed by the extraction of color, texture, and shape features, and classification using a Support Vector Machine (SVM). The system was trained and validated on a dataset of pomegranate fruit and leaf images, achieving high detection accuracy in the early stages of disease development. The results demonstrate that the proposed approach provides an efficient, reliable, and farmer-friendly tool for disease identification, thereby reducing agricultural losses and advancing smart, precision farming practices. The proposed system has significant practical value, particularly for smallholder farmers who lack access to expert agricultural guidance, as it offers a cost-effective, easy-to-use alternative to manual scouting. In future work, the system can be further enhanced by incorporating deep learning architectures such as Convolutional Neural Networks (CNNs) to improve detection accuracy and robustness. Additionally, deploying the technology as a mobile application would enable real-time, field-level disease diagnosis, making it more accessible to farming communities. The framework can also be extended to detect diseases in other fruit and vegetable crops, broadening its applicability and contributing to large-scale precision agriculture.

Keywords— Pomegranate; Image processing; SVM; Bacterial blight; leaf spot.