Conference Paper

Personalized portraits ranking.

DOI: 10.1145/2072298.2071993 In proceeding of: Proceedings of the 19th International Conference on Multimedea 2011, Scottsdale, AZ, USA, November 28 - December 1, 2011
Source: DBLP

ABSTRACT Portraits, also known as images of people, constitute an important part of consumer photos. Existing methods manage portraits based on either explicit objectives, e.g., a specified person or event, or aesthetics, i.e., the aesthetic quality of portraits. This paper presents a novel system for personalized portraits ranking. First, four kinds of personalized features, i.e., composition, clothing style, affection and social relationship are proposed to quantify users' intent. Then, example-based and sketch-based user interfaces (UI) are developed, which are capable of capturing users' personal intent hardly described by queries or aesthetics. Finally, portraits ranking is implemented by combing these features together with the developed user interfaces. Experimental results show that the system performs well in providing personalized preferences and the proposed features are effective for portraits ranking. From the user study, our system gets promising results.

0 Bookmarks
 · 
79 Views
  • [Show abstract] [Hide abstract]
    ABSTRACT: 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.
    Proceedings of the 27th Conference on Image and Vision Computing New Zealand; 11/2012