Multimedia Tools and Applications https://doi.org/10.1007/s11042-018-6715-9 Automatic and semi-automatic annotation of people in photography using shared events Anderson Almeida Firmino 1 · Cl´ audio de Souza Baptista 1 · Hugo Feitosa de Figueir ˆ edo 2 · Eanes Torres Pereira 1 · Brunna de Sousa Pereira Amorim 1 Received: 1 February 2018 / Revised: 15 August 2018 / Accepted: 21 September 2018 / © Springer Science+Business Media, LLC, part of Springer Nature 2018 Abstract This article proposes an automatic and semi-automatic annotation technique for people in photos using the shared event concept, which consists of many photos captured by different devices of people who attended the same event. The technique uses an algorithm to group photos into personal events and then verifies which of these events are shared. The auto- matic annotation of people uses techniques of facial recognition and detection, while the semi-automatic annotation uses a pondered sum of estimators based on contextual informa- tion and picture content. Experiments showed that using the shared event concept increases the hit rate of automatic and semi-automatic annotations of people in the utilized photo collection. Keywords People annotation · Face recognition · Event annotation · Context aware multimedia · Personal photo collection 1 Introduction A recent study by the Gartner group shows that smartphone sales surpassed one billion and five hundred units in 2017. 1 Because of the popularization of these devices and digital cameras, it is undeniable that digital photos have become part of our everyday routine. 1 https://www.gartner.com/newsroom/id/3859963  Anderson Almeida Firmino andersonalmeida@copin.ufcg.edu.br 1 Computer Science Department, Federal University of Campina Grande, Av. Aprigio Veloso, 882, Bodocongo - Campina Grande, Paraiba, 58109-900, Brazil 2 Federal Institute of Education, Science and Technology of Paraiba - Campus Esperanca, Esperanca, Para´ ıba, Brazil