hatem.abdellatif@urv.cat, domenec.puig@>rv.cat
mbstract
tory of potentially protected people. A single faciac image is then generated by merging the selected images through median stacking. Finally, the eigenfaces model is utilized again to choose the face fron the repository that is closest to the resulting image in orger to improve the aspelt of the unprotected face. Experimental results using a proprietary database and the public CALTECH, Utrecht and LFW face databases show the effectiveness of the proposed technique.
@Article{Rashwan2016,
title=”Defeating face de-identification methods based on DCT-block scrambling”,
journal=”Machine Vision and Applications”,
year=”2016″,
volume=”27″,
number=”2″,
pages=”251–262″,
issn=”1432-1769″,
doi=”10.1007/s00138-015-0743-5″,
url=”http://dx.doi.org/10.1007/s00138-015-0743-5″}
title=”Defeating face de-identification methods based on DCT-block scrambling”,
journal=”Machine Vision and Applications”,
year=”2016″,
volume=”27″,
number=”2″,
pages=”251–262″,
issn=”1432-1769″,
doi=”10.1007/s00138-015-0743-5″,
url=”http://dx.doi.org/10.1007/s00138-015-0743-5″}