The Union Public Service Commission (UPSC) has introduced facial recognition and Artificial Intelligence-based CCTV surveillance systems to prevent cheating and impersonation in its various tests. The commission has released a tender to invite bids from experienced public sector undertakings to devise two tech solutions to be used during the exam procedure. The first is Aadhaar-based fingerprint authentication (else digital fingerprint capturing) & facial recognition of candidates and QR code scanning of e-admit cards and the second is Live AI-based CCTV surveillance service.
The Union Public Service Commission (UPSC) conducts 14 major exams including the civil services examination to select officers of the Indian Administrative Service (IAS), Indian Foreign Service (IFS), and Indian Police Service (IPS) -- besides a number of recruitment tests, interviews every year for induction to Group ‘A’ and Group ‘B’ posts of the central government. Every year, Lakhs of candidates apply for these recruitment exams.
This year, it is expected that around 26 lakh candidates will appear in such recruitment exams, conducted at a maximum of 80 centres in Leh, Kargil, Srinagar, Imphal, Agartala, Aizawl and Gangtok, among other major cities.
'The UPSC attaches great importance to the conduct of its examinations in a free, fair, and impartial manner. In its endeavour to fulfil these objectives, the Commission intends to make use of the latest digital technology to match and cross-check the biometric details of the candidates and to monitor various activities of the candidates during the examination to prevent cheating, fraud, unfair means and impersonation,' read the tender document dated June 3, 2024.
One camera for 24 candidates
The Commission aims to enhance the examination process and prevent malpractice by candidates by introducing Aadhaar-based fingerprint authentication or digital fingerprint capturing, as well as facial recognition. Additionally, scanning of QR codes on e-admit cards and live AI-based CCTV video surveillance will be implemented. The selected service provider will use the data provided by the UPSC for Aadhaar-based fingerprint authentication of candidates and facial recognition during the exam. The system will also include a real-time attendance monitoring system and provision for monitoring the enrollment activity with GPS coordinates and time stamps to ensure compliance with shift timings. Facial recognition will involve comparing two images – one provided during online registration and another captured on the day of the exam.
The UPSC has announced that it will be implementing CCTV/video surveillance with recording and live broadcast systems to monitor the activities of candidates and staff involved in conducting the Commission's examinations at various centers/venues across the country. The service provider is required to install a sufficient number of CCTV cameras in every classroom (minimum 1 CCTV camera for 24 candidates), entry/exit gates, and control rooms of every examination venue. The control room is where pre-examination sensitive material will be kept and opened, and post-examination sensitive material will be packed.
The UPSC said that the service provider will install one CCTV camera for every 24 candidates at each exam hall/room subject to the condition that at least 1 CCTV camera is installed in every room irrespective of candidates being less than 24. In case of the exam hall/room having more than 24 candidates, one CCTV camera for every 24 candidates shall be installed ensuring that the CCTV camera-to-candidate ratio is not less than 1:24 and that there are zero blind spots, it added.
AI-Based CCTV Surveillance to be installed
AI-based CCTV surveillance will be able to track the movement at entry/exit gates during the exam and if the furniture inside the classrooms is not properly arranged. The video system will also alert the authorities if the cameras are offline or tempered (sic) by masking or black screen, 'if there is any movement in classrooms one hour before and after the exam, and if the invigilator is not moving after the specified time, as per the tender document. The AI should raise red flags at incidents that would indicate cheating, unfair means, absence of invigilators etc, it added. The date of closure of the bid document is July 7, 1 pm. The bid will be opened on the same day at 1.30 pm.
(With Inputs from PTI)
