Perfect Fingerprint Orientation Fields by Locally Adaptive Global Models

TL;DR

This paper introduces a novel globally adaptive model for fingerprint orientation fields that accurately captures the true OF with few parameters, enabling improved image processing and database management.

Contribution

The paper presents a new method combining global and local models to perfectly estimate fingerprint orientation fields with minimal parameters.

Findings

Model adapts to true OF in the limit

Enables high-fidelity low-parameter OF compression

Facilitates quick marking of poor quality OFs

Abstract

Fingerprint recognition is widely used for verification and identification in many commercial, governmental and forensic applications. The orientation field (OF) plays an important role at various processing stages in fingerprint recognition systems. OFs are used for image enhancement, fingerprint alignment, for fingerprint liveness detection, fingerprint alteration detection and fingerprint matching. In this paper, a novel approach is presented to globally model an OF combined with locally adaptive methods. We show that this model adapts perfectly to the 'true OF' in the limit. This perfect OF is described by a small number of parameters with straightforward geometric interpretation. Applications are manifold: Quick expert marking of very poor quality (for instance latent) OFs, high fidelity low parameter OF compression and a direct road to ground truth OFs markings for large databases, say. In this contribution we describe an algorithm to perfectly estimate OF parameters automatically or semi-automatically, depending on image quality, and we establish the main underlying claim of high fidelity low parameter OF compression.