Why facial recognition is a hit — and miss

Why facial recognition is a hit – and miss In response to a Right to Information (RTI) request in 2022, the Delhi Police had made public that it considered a match to be "positive" if its system demonstrated an accuracy rate of 80 per cent.

Key points

• 2 min read New Delhi Updated: Sep 4, 2026 05: 28 AM IST.
• Facial Recognition System (FRS) in a Delhi Police van parked near the Jantar Mantar protest site in July-end.
• At least 25 murder, rape accused whom Delhi Police software caught at Jantar Mantar were in jail, records show.
• The Delhi Police's facial recognition software places boxes around detected faces and compares them with images in police databases.
• Performance varies with the algorithm, camera angle, lighting, image quality, masks, and the database being searched.

Facial Recognition System (FRS) in a Delhi Police van parked near the Jantar Mantar protest site in July-end. (Express photo by Abhinav Saha).

Facial recognition systems analyse a person's facial features from an image or video, convert them into a unique digital template, and compare that template against images stored in a database. If the similarity score crosses a predefined threshold, the system flags a potential match for further verification.

Notably, the Delhi Police's facial recognition software places boxes around detected faces and compares them with images in police databases. In response to a Right to Information (RTI) request in 2022, the Delhi Police had made public that it considered a match to be "positive" if its system demonstrated an accuracy rate of 80 per cent.

In other words, the result is not, by itself, proof of identity.

Performance varies with the algorithm, camera angle, lighting, image quality, masks, and the database being searched. Testing by the US National Institute of Standards and Technology has discovered differences in error rates throughout demographic groups in plenty of algorithms. Human verification, audit trails, and clearly defined thresholds are therefore the key in this regard.

Apart from the Jantar Mantar protest, Delhi Police has applied the technology to identify residents suspected to have been involved in the 2020 riots, the clashes that broke out at Red Fort in 2021 during the farmers' protest and the Jahangirpuri riots in 2022.

Throughout India, digital surveillance systems are increasingly becoming a key part of modern policing, with law enforcement agencies deploying networks of CCTV cameras, facial recognition technology, drone-based monitoring, automated number plate recognition systems and AI-powered video analytics.

While authorities argue that such tools improve public safety and policing efficiency, their growing employ has additionally triggered concern among civil liberties groups over privacy, proportionality, transparency, and the absence of a comprehensive legal framework governing state- surveillance. © The Indian Express Pvt Ltd.

Taken together, the developments around why facial recognition is a hit point to a situation that is still moving, and the coming days should bring more clarity.