Close & Closer: Discover social relationship from photo collections

Author

Wu, Peng ; Ding, Weimin ; Mao, Zhidong ; Tretter, Dan

Author_Institution

Multimedia Interaction & Understanding Lab., HP Labs., Palo Alto, CA, USA

fYear

2009

fDate

June 28 2009-July 3 2009

Firstpage

1652

Lastpage

1655

Abstract

ldquoClose & Closerrdquo is a social imaging application that performs analysis on photo collections to reveal closeness of people´s relationship and presents the discovered relationship in an interactive manner to prompt photo sharing and people connection. It addresses two challenges with innovative solutions: first, a closeness measurement is proposed based on face detection and clustering result; Secondly, a computing framework is designed and implemented to execute computation extensive jobs, such as face detection and clustering, in a both distributed and parallel manner to assure the application´s usability. The application is deployed on Facebook social networking platform. The effectiveness of the closeness measurement and computing framework are validated through the real user experience.

Keywords

object detection; pattern clustering; social networking (online); Facebook social networking platform; face clustering; face detection; photo collection; photo sharing; social imaging application; Algorithm design and analysis; Clustering algorithms; Computer architecture; Concurrent computing; Distributed computing; Face detection; Facebook; Image analysis; Social network services; Usability; Social relationship; face clustering; face detection; photo collections;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia and Expo, 2009. ICME 2009. IEEE International Conference on

Conference_Location

New York, NY

ISSN

1945-7871

Print_ISBN

978-1-4244-4290-4

Electronic_ISBN

1945-7871

Type

conf

DOI

10.1109/ICME.2009.5202837

Filename

5202837