Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Automatic Privacy Classification of Personal Photos

: Buschek, D.; Bader, M.; Zezschwitz, E. von; Luca, A.E. de


Abascal, J.:
Human-computer interaction - INTERACT 2015. 15th IFIP TC 13 International Conference. Pt.2 : Bamberg, Germany, September 14 - 18, 2015; Proceedings
Cham: Springer International Publishing, 2015 (Lecture Notes in Computer Science 9297)
ISBN: 978-3-319-22667-5 (Print)
ISBN: 978-3-319-22668-2 (Online)
International Conference on Human-Computer Interaction (INTERACT) <15, 2015, Bamberg>
Fraunhofer FKIE ()

Tagging photos with privacy-related labels, such as “myself”, “friends” or “public”, allows users to selectively display pictures appropriate in the current situation (e.g. on the bus) or for specific groups (e.g. in a social network). However, manual labelling is time-consuming or not feasible for large collections. Therefore, we present an approach to automatically assign photos to privacy classes. We further demonstrate a study method to gather relevant image data without violating participants’ privacy. In a field study with 16 participants, each user assigned 150 personal photos to self-defined privacy classes. Based on this data, we show that a machine learning approach extracting easily available metadata and visual features can assign photos to user-defined privacy classes with a mean accuracy of 79.38 %.