MUMBAI, India, Oct. 26 -- Intellectual Property India has published a patent application (202631123738 A) filed by C. V. Raman Global University on October 15, 2026, for Trimodal Biometric Authentication Using Face Recognition, Air-Drawn Finger Gesture Password, And Voice Verification.
Inventors include Dr. Sampa Sahoo; Om Prasad Mahapatra; Jaydev Barik; Sourav Kumar Mohanty; Ayush Panda; and Dr. Ram Chandra Barik.
The application for the patent was published on October 23, 2026, under issue no. 43/2026.
Abstract: The present invention discloses a trimodal biometric authentication method and system that combines face recognition, an air-drawn finger gesture password and voice verification in a single contactless pipeline. During enrollment, face embeddings, multiple gesture samples and voiceprint samples of a user are captured and stored as encrypted, versioned templates in a template database. During authentication, a live face is matched using an embedding model with liveness and quality checks, a finger trajectory traced in the air over a displayed grid is tracked through hand landmarks, and a spoken random phrase is verified by a speaker embedding matcher. The gesture trajectory is normalized for scale, rotation and time and verified by sequence-consistency matching and timewindow validation. The three modality scores are supplied to a fusion and decision engine that applies staged or weighted score-level fusion with per-user calibrated thresholds. Adaptive policy modes allow either strict three-of-three verification or risk-based two-of-three verification with confidence constraints. Challenge-response prompts and modality-specific anti-spoof checks counter photograph, video and voice replay as well as random or impostor attempts. The system works with ordinary cameras and microphones, supports real-time on- device operation, and gives lower false acceptance and higher security than single-modal or simple two-factor systems.
Disclaimer: Curated by HT Syndication.
