Researchers have developed Bharat ABIS, an open-source system designed for large-scale, multi-modal biometric searches. This system integrates fingerprint, face, and iris data to create a unified template for efficient identity de-duplication. Evaluations on a massive dataset derived from India's Aadhaar database show promising accuracy, with a false negative identification rate of 0.3% at a 0.5% false positive identification rate. The system demonstrates impressive performance, achieving 100 searches per second on a gallery of 40 million identities using a single server equipped with Nvidia H100 GPUs. AI
Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →
IMPACT Demonstrates advancements in large-scale biometric search systems, potentially impacting identity verification and security infrastructure.
RANK_REASON The cluster contains an academic paper detailing a new system for large-scale biometric search.