MUMBAI, India, July 13 -- Intellectual Property India has published a patent application (202641082937 A) filed by Sr University, Warangal on July 06, 2026, for A System And Method For Deep Learning-Based Multi-Modal Biometric Authentication Using Biometric Feature Fusion And Presentation Attack Detection.
Inventors include Priyanka Madhiraju; Dr. Sasanko Sekhar Gantayat; and Dr. T. Raghunadha Reddy.
The application for the patent was published on July 10, 2026, under issue no. 28/2026.
Abstract: The present invention discloses a system and method for deep learning-based multi-modal biometric authentication using biometric feature fusion and presentation attack detection. The system acquires facial, fingerprint, and palmprint biometric data, performs preprocessing, extracts deep biometric representations, and integrates multiple biometric features through adaptive fusion techniques. A presentation attack detection module evaluates biometric authenticity using liveness analysis, texture consistency, and cross-modal correlation to identify spoofing attempts. Authentication decisions are generated only after successful biometric verification and presentation attack validation. The proposed integrated architecture enhances authentication accuracy, reduces false acceptance and rejection rates, improves spoof resistance, and provides reliable user authentication for secure access control applications across multiple domains.
Disclaimer: Curated by HT Syndication.
