Periodontal disease, also known as gum disease, is a common and serious condition affecting the tissues surrounding and supporting the teeth. It ranges from simple gum inflammation (gingivitis) to severe damage to the soft tissue and bone that supports the teeth (periodontitis), which can lead to tooth loss. Early detection and accurate classification of the stages of periodontal disease are crucial for effective treatment and prevention of further complications. This project aims to develop a deep learning-based system for the classification of periodontal disease using dental X-ray images and also focus on maximizing computational resource efficiency and speed by leveraging the benefits of one of the more recent transfer learning-based approaches, specifically MobileNets. By leveraging advanced convolutional neural networks (CNNs) and transfer learning techniques, the model will be trained and validated on a diverse dataset of dental X-ray images, ensuring robustness and generalizability across different patient demographics. The key objectives of this research include preprocessing and augmentation of dental X-ray images to enhance model performance, developing and fine-tuning a CNN architecture capable of extracting and learning relevant features from the images, implementing transfer learning using pretrained networks to improve classification accuracy, and evaluating the model’s performance using metrics. The successful implementation of this system could significantly aid dental professionals in the early diagnosis and treatment of periodontal disease, potentially improving patient outcomes and reducing the risk of severe oral health complications.