Automated Border Control System

Project Title

Automated Border Control System

Project Area of Specialization Artificial IntelligenceProject Summary

A fast automated biometric solution has been proposed to satisfy the future border control needs of airports resulting from the rapid growth in the number of passengers worldwide. Automated border control (ABC) systems handle the problems caused by this growth, such as congestion at electronic gates (e-gates) or delays in the planned arrival schedules. Different modalities, such as face, fingerprint, or iris recognition, will be used in most of the ABC systems located at airports.

Face recognition systems, installed in small kiosks inside the e-gates, require high quality facial images to allow high performance and efficiency. Accurate face recognition algorithms and OCR algorithms , which should be invariant to non-idealities, such as changes in pose and expression, occlusions, and changes in lighting, are also required for these systems.

Project Objectives

In order to meet this growth in passenger flow and air traffic, automated border control (ABC) systems have been installed at different worldwide airport entries and exits with the aim of facilitating travel while maintaining the security of international border crossing points. In an effort to work toward this harmonization, several practice guidelines have been published by different organizations, such as Frontex (technical and operational) (Frontex, 2012a), International Civil Aviation Organization (ICAO, 2015), the International Air Transport Association (IATA, 2016), and the European Committee for Standardization (CEN, 2015). Their objective is to create a definitive guide to ABC specifications and design based on human–computer interaction and safety aspects in Pakistan.

Project Implementation Method

Passengers arrive at the Automated Border Control System. The screen on the device indicates the passengers to lay down their Travel Document on the Document Reader in front of them. This is done through a GIF that describes the exact procedure of the process, to the passenger. If in case the document isn’t placed correctly, the system will indicate this message on the screen and will guide the passengers on how to properly record the document on the reader. After the travel document is scanned, the passenger is instructed to look at the camera positioned directly in front of his/her face. Wherein a GIF on the display screen will guide them on how they are instructed to record their face for the Facial Recognition System. In case of any error during the image capture, the screen will ask the passenger to repeat the process. After both the above processes are completed, the user will have to wait for a few moments until the system verifies the passenger. Upon confirmation the screen will display a green light, indicating successful user verification. But in case the user data doesn't match the data stored in the database, the screen will display a red light, indicat ing unsuccessful user verification (and an airport official will guide them on the later procedures that will happen).

Benefits of the Project

To make this interaction “touchless” in future, automated border control systems will be important. They allow for faster, safer and smoother checks, while ensuring that safe distancing is kept. Rather than waiting in a long queue to check-in for the flight, scan passports (and now review essential Covid-19 travel documentation), print boarding passes and bag drop luggage, customers can simply use one self-service kiosk solution to complete all of the above themselves. Automated Passport Kiosks efficiently manage passenger flow, whilst capturing imperative data and managing safe and secure access control. The implementation of automated self-service solutions optimise airport space and reduce queues, therefore minimising the time that passengers spend in close contact in the same space with each other, thus decreasing the opportunity for Covid-19 transmission.

Technical Details of Final Deliverable

Travel documents are one of the main factors in the border crossing process. It can identify through OCR algorithm using machine learning we extract MRZ( Machine Readable Zone) where all important passenger information is being stored. Face recognition systems, installed in the ABC systems, require high quality facial images to allow high performance and efficiency. Deep Learning and Machine learning model (CNN, ANN,Annoy, DeepFace… etc) with the help of pipeline of facial recognition algorithm able us and give accurate results which matches with passport image and current real-time image and identify passenger on run time. Biometric solution has been proposed to satisfy the future border control needs of airports resulting from the rapid growth in the number of passengers worldwide. ABC systems use unimodal biometric systems for access control and operate in two phases: enrolment and authentication. During the enrolment phase, the user’s biometric elements are acquired using a biometric reader and stored as a labelled template in a database. During the authentication phase the biometric patterns are captured for identification and verification of the user’s identity and issue registration card for automated border control system.

Final Deliverable of the Project HW/SW integrated systemCore Industry ITOther IndustriesCore Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development GoalsRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	50500
EPSON Workforce ES 60W	Equipment	1	25000	25000
Hiki Vision IP Camera	Equipment	1	5200	5200
Digital Persona 5100 USB Fingerprint Biometric Reader Scanner	Equipment	1	10500	10500
RFID Reader Writer	Equipment	1	9800	9800