Face recognition: A literature survey
ACM Computing Surveys (CSUR)
Attributing semantics to personal photographs
Multimedia Tools and Applications
Semantic structuring and retrieval of event chapters in social photo collections
Proceedings of the international conference on Multimedia information retrieval
Improving face clustering using social context
Proceedings of the international conference on Multimedia
Image annotation by leveraging the social context
Proceedings of the 5th International Conference on Ubiquitous Information Management and Communication
Learning people co-occurrence relations by using relevance feedback for retrieving group photos
Proceedings of the 1st ACM International Conference on Multimedia Retrieval
Personalized portraits ranking
MM '11 Proceedings of the 19th ACM international conference on Multimedia
Graph-based recognition in photo collections using social semantics
SBNMA '11 Proceedings of the 2011 ACM workshop on Social and behavioural networked media access
Photo identity tag suggestion using only social network context on large-scale web services
ICME '11 Proceedings of the 2011 IEEE International Conference on Multimedia and Expo
| Hi-index | 0.00 |
The field of genealogy has embraced the move towards digitisation, with increasingly large quantities of historical photographs being digitised in an effort to both preserve and share with a wider audience. Genealogy software is prevalent, but while many programs support photograph management, none use face recognition to assist in the identification and tagging of individuals. Genealogy is in the unique position of possessing a rich source of context in the form of a family tree, that a face recognition engine can draw information from. We aim to improve the accuracy of face recognition results within a family photograph album through the use of a filter that uses available contextual information from a given family tree. We also use measures of co-occurrence, recurrence and relative physical distance of individuals within the album to accurately predict the identity of individuals. This novel use of genealogical data as context has provided encouraging results, with a 26% improvement in accuracy at hit list size 1 and a 21% improvement at size 5 over the use of face recognition alone, when identifying 348 faces against a database of 523 faces from a challenging dataset of 173 family photographs.