Auflistung nach Autor:in "Drygajlo, Andrzej"
1 - 3 von 3
Treffer pro Seite
Sortieroptionen
- KonferenzbeitragDiscarding low quality minutia cylinder-code pairs for improved fingerprint comparison(BIOSIG 2015, 2015) Izadi, M. Hamed; Drygajlo, AndrzejLocal minutiae descriptors such as Minutia Cylinder-Code (MCC) are becoming increasingly popular in modern fingerprint verification systems. The verification performance depends on the fingerprint image quality in global and local levels. Discarding part of the lowest quality samples based on quality measures is a universal approach being widely used for improving the performance of biometric recognition systems. In this work, we evaluate several different discarding methods to filter out low quality pairs of MCC descriptors using minutiae qualities, with the final aim of improving global comparison accuracy. Moreover, we propose an efficient MCC based fingerprint comparison method based on discarding the low quality elements from local similarity matrix. Our extensive experiments on three different databases (FVC2002 DB2, FVC2002 DB3 and FVC2004 DB3) show that 1) the proper discarding of low quality MCC pairs from local similarity matrix either independently or using pairwise measures can improve the MCC based comparison performance, 2) for the proposed discarding method, the quality of central minutiae is more efficient as cylinder quality measure than the average minutiae qualities in each descriptor.
- KonferenzbeitragMeasuring performance in forensic automatic speaker recognition: VQ, GMM-UBM, i-vectors(Biosig 2016, 2016) Haraksim, Rudolf; Drygajlo, Andrzej
- KonferenzbeitragA template privacy protection scheme for fingerprint minutiae descriptors(BIOSIG 2013, 2013) Mirmohamadsadeghi, Leila; Drygajlo, AndrzejIt is important in biometric person recognition systems to protect personal data and privacy of users. This paper introduces a new mechanism to revoke and protect fingerprint minutiae information, which can be used in today's security-aware society. The recently developed minutiae cylinder code (MCC), which provides rotation and translation invariant descriptors for accurate fingerprint recognition by describing minutiae neighborhoods with respect to each other, is used as baseline fingerprint descriptor. A hybrid scheme combining a transformation and a user key is designed to provide the MCC-based fingerprint representation with revocability and irreversibility properties for template privacy protection across multiple applications. Furthermore, using the publicly available FVC datasets, it is demonstrated that the designed scheme improves the baseline accuracy of fingerprint recognition using the MCC method.