• DocumentCode
    182825
  • Title

    Multimodal Biometrics Using Cancelable Feature Fusion

  • Author

    Paul, Padma Polash ; Gavrilova, Marina

  • Author_Institution
    Dept. of Comput. Sci., Univ. of Calgary, Calgary, AB, Canada
  • fYear
    2014
  • fDate
    6-8 Oct. 2014
  • Firstpage
    279
  • Lastpage
    284
  • Abstract
    Multimodal Biometric system is very proficient because of the advantageous aspects over unimodal biometric system. Feature fusion based multimodal system is one of the best in its genres because it only stores single template and decries the privacy and security threats as well as the system memory. However, biometric templates from traditional feature fusion for multi-biometric systems are vulnerable in terms of template protection, where it can only improve the performance. On the other hand, proposed cancelable fusion is a new type of feature fusion for multimodal biometric system that can achieve both improved performance for multimodality and cancelability at the same time. In other word, proposed cancelable fusion keeps all the characteristics of multimodal biometric systems and ensures the template security in addition so that hackers cannot use the multi-biometric template to break the authentication system even if the template is compromised.
  • Keywords
    biometrics (access control); computer crime; data protection; message authentication; authentication system; cancelability; cancelable feature fusion; feature fusion based multimodal system; hackers; multibiometric template; multimodal biometric system; multimodality; privacy threats; security threats; system memory; template protection; template security; unimodal biometric system; Biometrics (access control); Cryptography; Databases; Ear; Face; Feature extraction; Cancelable Fusion; feature level fusio; multimodal biometric system; random projection;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Cyberworlds (CW), 2014 International Conference on
  • Conference_Location
    Santander
  • Print_ISBN
    978-1-4799-4678-5
  • Type

    conf

  • DOI
    10.1109/CW.2014.45
  • Filename
    6980772