ENHANCED AIRPORT BAGGAGE SCANNING PROCESS USING MACHINE LEARNING

As air travel increases and security threats rise, there is a critical need for more efficient baggage scanning systems at airports. This project enhances airport baggage scanning through machine learning to improve accuracy and speed in detecting prohibited items in luggage. We conducted a literature review to assess existing scanning technologies, identifying challenges such as high false positive rates and difficulties in detecting concealed threats. In response, we developed a machine learning framework utilizing advanced image processing and convolutional neural networks (CNNs) with a dataset of thousands of labeled X-ray images, enabling the model to recognize patterns linked to dangerous goods like firearms and explosives. The project features a user-friendly interface for security personnel, enabling quick responses to detected threats. By integrating machine learning with modern image processing, our system significantly enhances airport security, improves passenger safety, and streamlines baggage handling. In conclusion, this work demonstrates the potential of machine learning to transform airport security, offering a scalable solution to baggage screening challenges while ensuring compliance with safety regulations. Future efforts will focus on refining the model and conducting real-world deployment trials to evaluate effectiveness in various airport environments.