Abstract
The “friendship” relation, a social relation among individuals, is one of the primary relations modeled in some of the world’s largest online social networking sites, such as “FaceBook.” On the other hand, the “co-occurrence” relation, as a relation among faces appearing in pictures, is one that is easily detectable using modern face detection techniques. These two relations, though appearing in different realms (social vs. visual sensory), have a strong correlation: faces that co-occur in photos often belong to individuals who are friends. Using real-world data gathered from “Facebook,” which were gathered as part of the “FaceBots” project, the world’s first physical face-recognizing and conversing robot that can utilize and publish information on “Facebook” was established. We present here methods as well as results for utilizing this correlation in both directions. Both algorithms for utilizing knowledge of the social context for faster and better face recognition are given, as well as algorithms for estimating the friendship network of a number of individuals given photos containing their faces. The results are quite encouraging. In the primary example, doubling of the recognition accuracy as well as a sixfold improvement in speed is demonstrated. Various improvements, interesting statistics, as well as an empirical investigation leading to predictions of scalability to much bigger data sets are discussed.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We thank Microsoft External Research for providing seed funding for this project through its Human-Robot Interaction CFP.
- 2.
When viewed from a slightly different viewpoint, here we have a sensory grounding not of a conceptual entity (as is often the case in language grounding research), but of a social-level relation among entities, in a manner similar to grounding ontologies. Also, one might conjecture that the actual grounding of the social-level relation of friendship, might start during development initially from a restricted tangible meaning: that of the bodies of two individuals often being close and interacting. This restricted meaning is later extended during development in order to include social-level attributes that might include co-operation, sincerity,etc.
- 3.
The robot accepts friendships only from a selected circle at the moment.
- 4.
which we are not including in the experiments reported in this chapter. Interesting results regarding the transferability of training from camera- to facebook-photos and vice versa can be found in [6]. Also, results for hybrid training sets are included there.
- 5.
To our knowledge, Hiroshi Ishiguro first mentioned a similar problem for the case of a robot observing people [12].
- 6.
not enough observations for adequate knowledge
References
Mavridis N, Datta C, Emami S, BenAbdelkader C, Tanoto A, Rabie T (2009) FaceBots: social robots utilizing facebook. In: Proceedings of the 4th ACM/IEEE HRI ’09. ACM, New York, NY
Michelson J, Ortiz J (2006) Auto-tagging the Facebook. http://www.stanford.edu/class/cs229/proj2006/MichelsonOrtizAutoTaggingTheFacebook.pdf
Torralba A (2003) Contextual priming for object detection. Int J Comput Vision 53(2)(Jul 2003): 169–191
Hoiem D, Efros AA, Hebert M (2006) Putting objects in perspective. In: Proceedings of the 2006 IEEE computer society conference on computer vision and pattern recognition, Vol 2 (17–22 June 2006). CVPR. IEEE Computer Society, Washington, DC, pp 2137–2144
Stone Z, Zickler T, Darrell T (2008) Autotagging facebook: social network context improves photo annotation. IEEE computer society conference on computer vision and pattern recognition workshops, Anchorage, Alaska, USA, June 2008
Mavridis N, Kazmi W, Toulis P, Ben-AbdelKader C (2009) On the synergies between online social networking. Face recognition, and interactive robotics, CaSoN 2009
Facebook online social networking website. http://www.facebook.com
Facebook statistics. http://www.facebook.com/press/info.php?statistics
Samar V (1999) A single sign-on using cookies for Web applications. In: Proceedings of the 8th workshop on enabling technologies on infrastructure for collaborative enterprises table of contents, pp 158–163, ISBN:0-7695-0365-9
Nelson ML, Maly K (2001) Buckets: Smart objects for digital libraries. Commun. ACM 44, 5 (May 2001) 60–62
Facebook API. http://wiki.developers.facebook.com/index.php/Mainpage
Kanda T, Ishiguro H (2006) An approach for a social robot to understand human relationships: friendship estimation through interaction with robots. Interact Stud 7:369
Nelder JA, Mead R (1965) A simplex method for function minimization. Comput J 7:308–313
Viola P, Jones M (2004) Robust real-time object detection. Int J Comput Vision 57(2):137–154
Nefian AV, Hayes MH (1998) Hidden markov models for face detection and recognition, in International Conference on Image Processing, Chicago, Illinois, USA
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag London Limited
About this chapter
Cite this chapter
Mavridis, N., Kazmi, W., Toulis, P. (2010). Friends with Faces: How Social Networks Can Enhance Face Recognition and Vice Versa. In: Abraham, A., Hassanien, AE., Sná¿el, V. (eds) Computational Social Network Analysis. Computer Communications and Networks. Springer, London. https://doi.org/10.1007/978-1-84882-229-0_18
Download citation
DOI: https://doi.org/10.1007/978-1-84882-229-0_18
Published:
Publisher Name: Springer, London
Print ISBN: 978-1-84882-228-3
Online ISBN: 978-1-84882-229-0
eBook Packages: Computer ScienceComputer Science (R0)