Logo des Repositoriums

Auflistung nach Autor:in "Bischof, Horst"

1 - 2 von 2
  • Konferenzbeitrag
    A hybrid fingerprint verification matcher on card
    (BIOSIG 2003 – Biometrics and electronic signatures, 2003) Krivec, Vuk; Birchbauer, Josef; Marius, Wolfgang; Bischof, Horst
    Hybrid fingerprint matchers are well known as a powerful tool for high security applications where the reliability of a single fingerprint characteristic is not high enough for the intended application. In this paper, we propose a novel method, which due to its compressibility can be applied in memory constrained environments. This is important for application in smart cards and independent identification modules, which recently gained popularity. The proposed method uses minutia point matcher as the first stage of matching, and, after successfully completing this stage, the second stage of matching is based on comparing the homogeneity of a direction map. The direction map is compressed using a quad tree.
  • Konferenzbeitrag
    On Combining Classifiers for Assessing Portrait Image Compliance with ICAO/ISO Standards
    (BIOSIG 2008: Biometrics and Electronic Signatures, 2008) Storer, Markus; Urschler, Martin; Bischof, Horst; Birchbauer, Josef A.
    The International Civil Aviation Organization (ICAO) has selected biomet- rics - in particular face - as the technique for travel documents to verify the association between such documents and the person in possession of them. The International Stan- dard Organization (ISO) has defined a standard for the digital face images to be used in Machine Readable Travel Documents. Due to the ISO/IEC 19794-5 international standard, there exists a high demand for automatically checking portrait images to as- sist civil service employees in decision making regarding ICAO/ISO compliance. We present a face normalization and analysis system implementing several requirements of the ISO/IEC 19794-5 specification. We address the criteria eyes-open and mouth- closed and highlight the fusion of complementary classifiers to boost performance of the overall analysis system. Our results show that classifier fusion is capable of im- proving the classification performance considerably as compared to a single classifier decision.