Logo des Repositoriums

Auflistung nach Autor:in "Yang, Bian"

1 - 2 von 2
  • Konferenzbeitrag
    A fingerprint indexing scheme with robustness against sample translation and rotation
    (BIOSIG 2015, 2015) Li, Guoqiang; Yang, Bian; Busch, Christoph
    Automatic fingerprint identification systems (AFIS) are getting prevalent around the world, and the size of fingerprint databases involved in AFIS is continuously growing. Thus, studying fingerprint indexing algorithms is desirable in order to facilitate the search process in a large-scale database. In this paper, we firstly propose a feature extraction method to generate a binary template based on minutia information. A fingerprint indexing is designed by combining this binary template and Locality Sensitive Hashing indexing algorithm developed in a state-of-the-art fingerprint indexing method (minutia cylinder-code based indexing method). Experiments have been conducted on several public databases with different settings. The results show that the proposed approach achieves competitive performance or even better performance when benchmarked to the state-of-the-art fingerprint indexing methods.
  • Konferenzbeitrag
    Protected Honey Face Templates
    (BIOSIG 2015, 2015) Martiri, Edlira; Yang, Bian; Busch, Christoph
    Most existing biometric template protection schemes (BTPS) do not provide as strong security as cryptographic tools; and furthermore, they are rarely able to detect during a verification process whether a probe template has been leaked from the database or not (i.e., being used by an imposter or a genuine user). By using the “honeywords” idea, which was proposed to detect the cracking of hashed password database, we show in this paper how to enable the detectability of biometric template database leakage. We add an extra layer of protection since biometric features cannot be renewed. The biometric system design implies that protection mechanisms must satisfy the irreversibility property and to this respect we apply different correlation tests to show the non-distinguishability between genuine and honey templates. In this paper we implement the idea of a honey template protection scheme on faces and evaluate the security and accuracy performance.