The National Crime Records Bureau (NCRB) has planned to establish a National Automated Facial Recognition System (AFRS). The tender for this was notified on July 8, and will close on November 8.
“This is an effort in the direction of modernising the police force, information gathering, criminal identification, verification and its dissemination among various police organisations and units across the country,” said an NCRB RFP note.
During a trial run of facial recognition system in April last year, Delhi Police identified almost 3,000 missing children in just four days.
The benefits of the system will be “a robust system for identifying criminals, missing children /persons, unidentified dead bodies and unknown traced children/persons all over the country; a repository of photographs of criminals in the country; enhanced ability to detect crime patterns and modus operandi across the states and communicate to the state police departments for aiding in crime prevention”.
Currently, the leading face recognition software are Amazon Rekognition, Face Recognition and Face Detection by Lambda Labs, Microsoft Face API, Google Cloud Vision and IBM Watson Visual Recognition.
The Automated Facial Recognition System (AFRS) will help in automatic identification and verification of persons from digital images, photos, digital sketches, video frames and video sources by comparison of selected facial features of the image from an already existing image database, the NCRB said.
“A facial recognition system is a great investigation enhancer for identification of: criminals, missing children/persons, unidentified dead bodies and unknown traced children/persons. It can provide investigating officers of the civil police with the required tools, technology, and information,” said NCRB.