Lung cancer remains one of the leading causes of cancer related deaths worldwide, largely due to late-stage diagnosis. This project presents a machine learning-based system for the early detection of lung cancer using CT and X- ray images. The system utilizes two supervised learning algorithms Logistic Regression and Support Vector Machine (SVM) to classify lung images as either normal or cancerous. Key preprocessing steps, including grayscale conversion, resizing, normalization, and flattening, is applied to standardize the input data. Feature engineering techniques such as standardization and label encoding further enhance the model’s learning capability. Both models are trained and evaluated using labeled image data, achieving outstanding results with 100% accuracy on the test set. A single-image prediction module is also developed to enable real-time diagnosis, outputting a simple “Yes” or “No” based on the model's prediction. The system is lightweight, accurate, and user-friendly, offering potential integration into real-world clinical workflows. This work serves as a foundational step toward deploying AI-assisted lung cancer diagnosis systems in healthcare environments.