Development of social media has created a great opportunity for the users to share photos, textual messages or contents and videos to maintain a social connection with each other in Online Social Networks. However, a photo may contain rich information like Identity of the person, number plates etc. which makes it easier for malicious viewer to interfere in these sensitive information. Sharing a photo involves multiple users, so the publisher should take into account of the privacy of all related users. The main aim of this paper is to anonymize the photo so the users who may experience privacy loss due to the photo sharing will not be identified. We use Haar Cascade which is a machine learning based approach where a lot of positive and negative images are used to train the classifier. This technique is used to detect the faces and number plates. A User Identification Lock is provided before sharing or posting a content so as to ensure whether the photo or other textual information is posted by the actual owner or not. This project ensures the users personal information and other important contents are not violated.

Keywords : Anonymization, Online Social Networks, Haar Cascade.