On Adaptive Fingerprint Pore Extraction

Pore extraction appears to play an important role in latent (or fragmentary) fingerprint examination and in applications involving large population or high security levels. In this paper, we introduce a novel pore extraction approach designed to deal with anisotropic fingerprint aspects, which can be used to detect both closed and open pores. The method combines the directional field information with a toggle mapping to estimate fingerprint ridges location. It has proved to be very robust to noise and, as we will show through some experiments, it outperforms well-known state-of-the-art methods. Although we illustrate its application only on a specific database, our approach is quite general, simple and can be easily extended to others image applications involving similar feature extraction.