A study on fuzzy clustering-based k-anonymization for privacy preserving crowd movement analysis with face recognition
Katsuhiro Honda, Masahiro Omori, Seiki Ubukata, Akira Notsu · 2015
k-anonymization is a basic technique for privacy preserving data analysis of personal information. This paper studies the applicability of a fuzzy clustering-based anonymization approach to crowd movement analysis, in which each individual movement is captured through face recognition in camera images. Before utilizing each face feature values, k-anonymization is performed by coding cluster elements, which are extracted by fuzzy k-member clustering. In an experimental study, the advantage and availability of fuzzy partitions are investigated through comparisons of reproduction qualities and anonymization costs with several fuzzy degree settings.