Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

FaceHash: Face detection and robust hashing

: Steinebach, M.; Liu, H.; Yannikos, Y.


Gladyshev, P.:
Digital Forensics and Cyber Crime. Fifth International Conference, ICDF2C 2013 : Moscow, Russia, September 26-27, 2013, Revised Selected Papers
Cham: Springer International Publishing, 2014 (Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 132)
ISBN: 978-3-319-14288-3 (Print)
ISBN: 978-3-319-14289-0 (Online)
International Conference on Digital Forensics and Cyber Crime (ICDF2C) <5, 2013, Moscow>
Fraunhofer SIT ()

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.