Plant diseases pose a significant threat to global agriculture, often resulting in reduced crop yields and economic losses. Early and accurate identification of plant leaf diseases is crucial for implementing effective mitigation strategies. This study explores the application of Convolutional Neural Networks (CNNs), a deep learning technique, to automate the detection and classification of plant leaf diseases. Using a dataset comprising images of healthy and diseased leaves, the proposed model was trained to identify various disease types with high accuracy. The CNN architecture leverages feature extraction and pattern recognition capabilities to distinguish subtle variations in leaf textures, colors, and patterns. Results demonstrate the model's robustness in achieving precision and recall rates exceeding 90%, highlighting its potential as a reliable tool for farmers and agricultural professionals. This research underscores the transformative role of CNNs in smart farming, enabling timely interventions and fostering sustainable agricultural practices. Future work involves expanding the dataset, improving generalizability, and integrating the system into real-time monitoring tools