MUMBAI, India, Jan. 23 -- Intellectual Property India has published a patent application (202511126509 A) filed by Swami Rama Himalayan University, Dehradun, Uttarakhand, on Dec. 14, 2025, for 'a system for multimodal biometric authentication using decoupled model architecture and adaptive decision-level fusion.'
Inventor(s) include Sameer Rajesh Chavan; Dr. Deepak Srivastava; Dr. Pramod Kumar; and Dr. Shachi Mall.
The application for the patent was published on Jan. 23, under issue no. 04/2026.
According to the abstract released by the Intellectual Property India: "The invention relates to a multimodal biometric authentication system in the field of secure identity verification. Biometric data acquisition modules capture facial, fingerprint, iris, voice, or gait data, which are processed by modality-specific preprocessing pipelines to reduce noise and enhance data quality. Independent processing units utilize deep learning models-including convolutional neural networks for facial recognition and recurrent or transformer-based architectures for voice-to extract discriminative features. An adaptive decision-level fusion module dynamically assigns weights based on signal quality and confidence scores, computing an aggregate authentication score that is communicated to a system integration module for the final authentication decision. This architecture enables robust, scalable, and efficient multimodal biometric verification with enhanced accuracy and security."
Disclaimer: Curated by HT Syndication.
