Nowadays, more and more people would like to play the social network. Social network is a set of people (or organizations or other social entities) connected by a set of socially-meaningful relationships. People can share their life experience, notify friends about themselves, play game and share photos with their friends internationally. But before interacting with each other, they need to form the relationship. This thesis presents the idea of construct a social network that makes use of the image analysis. In traditional social network application, friend relationship can only be established with text-based information, such as email, name or other personal information. However, we found that only text-based information is insufficient in social network. For example, if user A and user B meet in an event and they take a photo with each other but they forget to get the contact information. In the current social network application, they cannot to establish relationship through the social network. But in my concept, we can adopt face recognition to solve such problem. With such technology, friend relationship can be established without the need of having the text-based information of a user, friend recommendation algorithm can be more accurate, and face tagging can be done automatically.