Muhammad Taha Tahir, Muhammad Hessan Butt and Muhammad Nouman2025-10-022025-10-022024https://escholar.umt.edu.pk/handle/123456789/7798The study investigates the application of machine learning techniques for detecting surface defects on aircraft metal and composite surfaces. The methodology involved selecting, training, and testing using YOLO V9, on datasets containing both general and aircraft-specific defects. YOLO was chosen for its real-time processing capabilities and high accuracy. The results showed significant improvements in defect detection accuracy and efficiency, with the final model achieving high precision for cracks, scratches, and corrosion. The development of an intuitive user interface further ensures accessibility for maintenance personnel, highlighting the potential of integrating advanced machine learning techniques into aircraft maintenance to improve inspection processes.enThesis