Several government agencies across the country have started using Aadhaar identity to authenticate beneficiaries of different schemes. The Telangana government, which attracted criticism from privacy activists for allegedly using facial recognition software without legal sanction, has developed a method to authenticate its beneficiaries, using Artificial Intelligence, Machine Learning, Big Data and Deep Learning solutions.
To start with, the State government has implemented the RTDAI (Realtime Digital Authentication of Identity) in authenticating pensioners without any need for special hardware at the user end. It doesn’t require fingerprints or iris images to authenticate a person.
“All you need to have a smart phone to remotely authenticate yourself. Take a photo and upload it in the exclusive app launched for the purpose. The software will verify the photo and demographic details in the pension database, avoiding the need to authenticate people physically,” GT Venkateshwar Rao, Managing Director, Telangana State Technology Services (TSTS), has said.
The app is made available in T App Folio, the umbrella app for various e-governance offerings from Telangana Government.
Those who consent to use the IT-backed authentication solution can avail of the service.
The whole process takes just under one minute to find answers for the two crucial questions in authenticating a pensioner – Whether the pensioner in question is alive? Is she or he the legitimate pensioner?
The technological tools could address the challenges such as old pictures in the data base versus the latest photos of users. The system can take care of the changes happened over a period of time in faces. The same case with the names. For example, the system can match K Aseervadam with Aseervadam Karra as it checks other parameters available in the data available with the department in question.
Three-factor authentication
The Pensioners Life Certificate Authentication using a Selfie (PLCS) method deploys three levels of authentication – demographics (name, father’s name and address), photo and liveness. The TSTS is using an Artificial Intelligence-based liveness check solution developed by a Bengaluru start-up and a Machine Learning-based demographic comparison solution.
Post one-time registration (consent) and authentication, the user can authenticate himself from anywhere and anytime he or she is asked to.
The government claims the success rate in authentication of pensioners is about 93 per cent. Of the 13,759 applicants, the system could successfully authenticate 12,763 pensioners. “The system would learn over a period of time and the success rate could be improved as it learns. The success rate could be as high as 96-98 per cent,” Venkateshwar Rao, who is also Commissioner (Electronic Service Delivery), said.
He was showcasing the solution at a seminar on Artificial Intelligence and Blockchain for Efficient Public Service Delivery.
The AI, ML and deep learning solutions would quickly check the details submitted by the user with the information piled up in public data systems.
He said the use cases could be many. Deployment of this method in authenticating the voters is one.