Perfect Fingerprint Orientation Fields by Locally Adaptive Global Models
This work addresses the need for accurate OF estimation in fingerprint recognition systems, which is crucial for applications like image enhancement and matching, though it appears incremental as it builds on existing OF modeling techniques.
The paper tackles the problem of estimating fingerprint orientation fields (OFs) by proposing a novel approach that combines global modeling with locally adaptive methods, achieving perfect adaptation to the 'true OF' in the limit and enabling high-fidelity low-parameter compression.
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.