Image sharing is the new cool feature which is successful in ruling Online Social Networks (OSNs). Unknowingly, it
may expose users¶ privacy if they can post, comment, and tag a photo without any restriction. In this paper, we are attempting to
address this issue and study the scenario when a user shares a photo containing individuals¶ other than himself/ herself (referred as
co-photo for short). To refrain the possible privacy leakage of a photograph, we are suggesting an approach to entitle everyone in a
photo to acknowledge the act of image posting and enable them to be a decisive authority on the photo sharing. To achieve this feat,
we require coherent facial recognition (FR) system to identify everyone in the photo. However, as the need of the privacy concerns
in people increases it may limit the publicly available photos to train the FR system. To deal with this trauma, we suggest an approach
to consider private photos to design personalized FR system which can be trained to recognize possible co-owners without
compromising their privacy. With our suggested approach, we think the computational complexity will reduce as we are not relying
on the photos available on social platform for the training purpose but instead asking users to provide their photos from their gallery
which is reliable source and the private training set is also not exposed on the platform to maintain secrecy about this dataset.
Published In:IJCSN Journal Volume 6, Issue 6
Date of Publication : December 2017
Pages : 694-701
Tables : --
Nirajkumar Kunturkar : received B.Tech. from COEP, Pune
university in Information Technology. At Present he is pursuing
M.E. in department of Computer Science and Engineering,
P.E.S. College of Engineering, Aurangabad, MS-India.
S. N. Kakarwal : received Ph.D., M.E. and B.E. degree in Computer
Science and Engineering. She Presently working as Professor
in Department of Computer Science and Engineering,
P.E.S. College of Engineering, Aurangabad, MS-India. Her
research interests include Image Processing, Pattern Recognition
and Artificial Neural Network. In these areas, she has
published 28 research papers in leading Journals, National and
International conferences proceedings. She has bagged 3 Best paper award.
Online social networks, FR system, Open social, privacy
Photo sharing is amongst the top activities on online
social networks such as facebook and it has got lot of
popularity in recent times. Unfortunately, and unwillingly
careless photo post, may reveal individual¶s
privacy appearing in a photo. To get rid of the privacy
concern, we have proposed an approach which enables
everyone appearing in a photo to give permission before
photo is getting posted publicly on a platform. We
have designed a privacy preserving FR system to identify
each individual in a photo. This system has pure
confidentiality of the photos used for training. We have
carried out experiment with standard database to show
the effectiveness and the capability of the system to
protect the privacy of the user. The analysis carried out
shows the efficiency of the system; with the Face94db
we observed that the identification of a user when his
photo is given to the system it identified the user correctly
in all of the three Eigen, RGB pixel comparison
and fisher algorithms correctly. All of the test data for
11 users; 5 photos each recognized correctly.
 M. Ames and M. Naaman. Why we tag: Motivations
for annotation in mobile and online media In
V. Shoup, editor, CRYPTO, volume 3621 of Lecture
Notes in Computer Science, pages 241±257.
 Z. Stone, T. Zickler, and T. Darrell. Autotagging
facebook: Social network context improves photo
annotation. In Computer Vision and Pattern
Recognition Workshops, 2008. CVPRW¶08. IEEE
Computer Society Conference on, pages 1±8.
 L. Kissner and D. X. Song. Privacy-preserving set
operations. In V. Shoup, editor, CRYPTO, volume
3621 of Lecture Notes in Computer Science, pages
241±257. Springer, 2005.
 A. Acquisti and R. Gross. Imagined communities:
Awareness, information sharing, and privacy on
the Facebook. MCS¶05, pages 278±285, Berlin,
Heidelberg, 2005. Springer-Verlag.
 Over-exposed? Privacy patterns and considerations
in online and mobile photo sharing.
S. Ahern, D. Eckles, N. S. Good, S. King, M.
Naaman, and R. Nair. Trends Mach. Learn.,
3(1):1±122, Jan. 2011.
 J. Bonneau, J. Anderson, and G. Danezis Prying
data out of a social network OTM 2006 Workshops,
volume 4278 of Lecture Notes in Computer Science,
pages 1734±1744. Springer Berlin Heidelberg, 2006.
 M. E. Newman. The structure and function of complex
networks. SIAM review, 45(2):167±256, 2003.
 A. Besmer and H. Lipford. Tagged photos: Concerns,
perceptions, and protections. In Proceedings
of the SIGCHI Conference on Human Factors in
Computing Systems, CHI ¶10, New York, NY,
USA, 2012. ACM.
 K. Choi, H. Byun, and K.-A. Toh. A collaborative
face recognition framework on a social network
platform. In Automatic Face Gesture Recognition,
2008. FG ¶08. 8th IEEE International Conference
on, pages 1±6, 2008.
 Z. Stone, T. Zickler, and T. Darrell. Toward largescale
face recognition using social network context.
Proceedings of the IEEE, 98(8):1408±1415.
 Detecting Social
Cliques for Automated Privacy Control in Online
All rights reserverd @ IJCSN International Journal www.IJCSN.org