MUMBAI, India, Oct. 26 -- Intellectual Property India has published a patent application (202611112710 A) filed by Dr. Avadhesh Kumar Gupta; Amrita Tiwari; Rekha Baghel; Dr. Amrita Bhatnagar; Dr. Alka Verma; and Manoj Kumar on September 20, 2026, for Centroid-Anchored Multi-Resolution Grid-Based Method And System For Rotation-Invariant Statistical Fingerprint Template Position Allocation.

Inventors include Dr. Avadhesh Kumar Gupta; Amrita Tiwari; Rekha Baghel; Dr. Amrita Bhatnagar; Dr. Alka Verma; and Manoj Kumar.

The application for the patent was published on October 23, 2026, under issue no. 43/2026.

Abstract: [073] The present invention relates to a centroid-anchored multi-resolution grid-based method and system for rotation-invariant statistical fingerprint template position allocation. The system receives fingerprint data, extracts fingerprint features with associated spatial coordinates and confidence values, determines a representative centroid of the feature distribution, transforms the feature coordinates into a centroid-relative reference domain, and encodes the transformed features using rotation- independent spatial information. A plurality of spatial grids having different resolutions are generated about the centroid, and the fingerprint features are allocated to corresponding grid positions. Statistical values including feature occupancy, confidence-weighted density, feature-type distribution, radial characteristics, orientation characteristics and reliability may be generated for the grid positions. Boundary-aware allocation may distribute a feature contribution across neighboring cells to reduce sensitivity to small spatial displacement. Statistical representations from coarse, intermediate and fine resolutions are combined to form a hierarchical fingerprint template suitable for biometric verification, identification and indexing. The invention provides a compact and robust fingerprint representation with reduced sensitivity to translation, rotation, local displacement, partial acquisition and feature uncertainty. Accompanied Drawing [FIGS. 1-2]

Disclaimer: Curated by HT Syndication.