Abstract
Recently, with the rapid development of Internet technology, Social Network Service (SNS) has blossomed into a worldwide popularity. In this paper, we present a novel application for friend recommendation on SNS websites. Unlike the questionnaire based friend recommendation scheme used nowadays (e.g. online dating sites, online matchmaking sites), we focus on the fact that most of the online users may be interested with the strangers whose appearances are somehow attractive according to their own preferences. Therefore, we present a friend recommendation system based on the appearances on photos, which aims to "make friend by the first sight". The system is built upon 5000 portraits photos as source dataset with another 50 photos as training set. Once the user provides rating to several photos in the training set, we first build his/her appearance preference model based on face detection and multi-features co-operation. Then, the images in the source are ranked according to different features respectively. Finally, the results of multi-features are fused via the method of Borda count. The system is a useful complement to the conventional psychological tests based friend recommendation scheme. It is easy to play with and of a lot of fun.
