Digital Forensics and Cyber Crime. Fifth International Conference, ICDF2C 2013, Moscow, Russia, September 26-27, 2013, Revised Selected Papers

Research Article

FaceHash: Face Detection and Robust Hashing

Download
682 downloads
  • @INPROCEEDINGS{10.1007/978-3-319-14289-0_8,
        author={Martin Steinebach and Huajian Liu and York Yannikos},
        title={FaceHash: Face Detection and Robust Hashing},
        proceedings={Digital Forensics and Cyber Crime. Fifth International Conference, ICDF2C 2013, Moscow, Russia, September 26-27, 2013, Revised Selected Papers},
        proceedings_a={ICDF2C},
        year={2015},
        month={2},
        keywords={Robust image hash Face detection Blob detection},
        doi={10.1007/978-3-319-14289-0_8}
    }
    
  • Martin Steinebach
    Huajian Liu
    York Yannikos
    Year: 2015
    FaceHash: Face Detection and Robust Hashing
    ICDF2C
    Springer
    DOI: 10.1007/978-3-319-14289-0_8
Martin Steinebach1,*, Huajian Liu1, York Yannikos1
  • 1: Fraunhofer SIT
*Contact email: martin.steinebach@sit.fraunhofer.de

Abstract

In this paper, we introduce a concept to counter the current weakness of robust hashing with respect to cropping. We combine face detectors and robust hashing. By doing so, the detected faces become a subarea of the overall image which always can be found as long as cropping of the image does not remove the faces. As the face detection is prone to a drift effect altering size and position of the detected face, further mechanisms are needed for robust hashing. We show how face segmentation utilizing blob algorithms can be used to implement a face-based cropping robust hash algorithm.