MUMBAI, India, July 30 -- Intellectual Property India has published a patent application (202621066912 A) filed by Sctr'S Pune Institute Of Computer Technology, Pune; Sharvil Chirputkar; Vaibhav Rahalkar; Dr. Prahlad Tirumalarao Kulkarni; and Mrs. Deepali Prashant Salapurkar on May 27, 2026, for Multi-View Context-Aware Crowd Attendance Determination System Using Ptz-Based Facial Recognition Processing.
Inventors include Sharvil Chirputkar; Vaibhav Rahalkar; Dr. Prahlad Tirumalarao Kulkarni; and Mrs. Deepali Prashant Salapurkar.
The application for the patent was published on July 24, 2026, under issue no. 30/2026.
Abstract: ABSTRACT MULTI-VIEW CONTEXT-AWARE CROWD ATTENDANCE DETERMINATION SYSTEM USING PTZ-BASED FACIAL RECOGNITION PROCESSING The present invention relates to a crowd attendance determination system (100) and method (200) for automated attendance management using multi- view facial recognition within monitored environments. The system (100) comprises one or more imaging devices (110) including a pan-tilt-zoom camera configured to sequentially traverse predefined positional presets corresponding to different regions within a monitored environment for acquiring image data from multiple viewpoints. A processor (120) detects facial regions from the acquired image data, generates facial feature embeddings using trained deep-learning facial recognition models, and performs similarity matching against filtered candidate identities stored within a vector database. Session-specific contextual metadata retrieved from a metadata repository is utilized to restrict identity matching operations to authorized participants associated with an attendance session, thereby reducing computational complexity and false-positive detections. The system (100) further performs cross-view identity reconciliation to eliminate duplicate detections generated across multiple viewpoints. (To be published along with FIG. 1)
Disclaimer: Curated by HT Syndication.
