Automatic Privacy Classification of Personal Photos

Abstract : 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 %.
Type de document :
Communication dans un congrès
15th Human-Computer Interaction (INTERACT), Sep 2015, Bamberg, Germany. Lecture Notes in Computer Science, LNCS-9297 (Part II), pp.428-435, 2015, Human-Computer Interaction – INTERACT 2015. 〈10.1007/978-3-319-22668-2_33〉
Liste complète des métadonnées

Littérature citée [11 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01599867
Contributeur : Hal Ifip <>
Soumis le : lundi 2 octobre 2017 - 15:41:33
Dernière modification le : mardi 3 octobre 2017 - 14:45:58

Fichier

346942_1_En_33_Chapter.pdf
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Citation

Daniel Buschek, Moritz Bader, Emanuel Zezschwitz, Alexander Luca. Automatic Privacy Classification of Personal Photos. 15th Human-Computer Interaction (INTERACT), Sep 2015, Bamberg, Germany. Lecture Notes in Computer Science, LNCS-9297 (Part II), pp.428-435, 2015, Human-Computer Interaction – INTERACT 2015. 〈10.1007/978-3-319-22668-2_33〉. 〈hal-01599867〉

Partager

Métriques

Consultations de la notice

25

Téléchargements de fichiers

18