Photo sharing is an attractive feature in Online Social Networks (OSNs) but it may leak users privacy if they are allowed to post, comment, and tag a photo freely. This issue of sharing the photos of individual or himself/herself is addressed by the proposed scheme. The proposed scheme is used to prevent possible privacy leakage of a photo. For this purpose, an efficient facial recognition (FR) system is required that can recognize everyone in the photo. However, to train the FR system, more

more »

... anding privacy setting may limit the number of the photos that are publicly available. To solve this problem, the proposed scheme attempts to utilize users private photos by designing a personalized FR system and also provide security while posting the photo. A distributed consensus based method is also developed to reduce the computational complexity and protect the private training set. The efficiency of proposed scheme is calculated by using recognition ratio. The proposed mechanism is implemented as a proof of concept on Android application in OSN's (Online Social Networks) on Facebook platform. 513 at the same time. The main focus is to let each user only deal with his/her private photo set as the local train data which can be used by the users to learn out the local training result. Once the local training results are achieved then it can be exchanged among various users to form a global knowledge. In the next round, each user learns over his/hers local data again and takes the global knowledge as a reference. Finally the information is spread over users and consensus can be reached [10] . II. RELATED WORK N. Mavridis, w. Kazmi, and p. Toulis[1] Study the statistics of photo Sharing on social networks and propose a three realms Model: "a social realm, in which identities are entities, And friendship a relation; second, a visual sensory realm, Of which faces are entities, and co-occurrence in images A relation; and third, a physical realm, in which bodies Belong, with physical proximity being a relation." They show that any two realms are highly correlated. Given information in one realm, we can give a good Estimation of the relationship of the other realm. Z. Stone, t. Zickler, and t. Darrell[2] Propose to use The contextual information in the social realm and cophoto Relationship to do automatic fr. They define a Pairwise conditional random field (crf) model to find The optimal joint labeling by maximizing the conditional Density. Specifically, they use the existing labeled photos As the training samples and combine the photo cooccurrence Statistics and baseline fr score to improve The accuracy of face annotation. K. Choi, h. Byun, and k.-a. Toh [3] Discuss the difference between the traditional FR system and the FR system that is designed specifically for OSNs. They Point out that a customized FR system for each user is Expected to be much more accurate in his/her own photo Collections. J. Y. Choi, w. De neve, k. Plataniotis, and y.-m[4] propose a novel collaborative face recognition (FR) framework, improving the accuracy of face annotation by effectively making use of multiple FR engines available in an OSN. Their collaborative FR framework consists of two major parts: selection of FR engines and merging (or fusion) of multiple FR results. The selection of FR engines aims at determining a set of personalized FR engines that are suitable for recognizing query face images belonging to a particular member of the OSN. For this purpose, they exploit both social network context in an OSN and social context in personal photo collections. In addition, they devise two effective solutions for merging FR results, adopting traditional techniques for combining multiple classifier results. D. Rosenblum[5] The privacy leakage caused by The poor access control of shared data in web 2.0 is Well studied. C. Squicciarini, m. Shehab, and f. Paci [6] Propose a Game-theoretic scheme in which the privacy policies are collaboratively enforced over the shared data. Each user is able to define his/her privacy policy and exposure Policy. Only when a photo is processed with owner's Privacy policy and co-owner's exposure policy could it be posted. K. Thomas, C. Grier and D. M. Nicol [7] examine how the lack of joint privacy controls over content can inadvertently reveal sensitive information about a user including preferences, relationships, conversations, and photos. They analyze Facebook to identify scenarios where conflicting privacy settings between friends will reveal information that at least one user intended remain private. they show how Facebook's privacy model can be adapted to enforce multi-party privacy and present a proof of concept application built into Facebook that automatically ensures mutually acceptable privacy restrictions are enforced on group content. A. Besmer and H. Richter Lipford [8] examine privacy concerns and mechanisms of tagged images. Using a focus group they explored the needs and concerns of users for tagged photo privacy. They also designed a privacy enhancing mechanism and validated it using a mixed methods approach. Their results identify the social tensions that tagging generates, and the needs of privacy tools to address the social implications of photo privacy management.