Picseek - collaborative filtering for context-based image recommendation

Abstract

As the World Wide Web becomes a large source of images, the image recommendation system has got a great demand. There are several image recommendation systems for both commercial and academic areas, which deal with the preference as fixed. However, since the Images preferred by a user may change depending on the contexts, the conventional systems have inherent problems. This paper proposes a contextaware image recommendation service (picSEEK) that exploits the collaborative-filtering to recommend appropriate images with respect to the context. We have analyzed the recommendation process and performed a subjective test to show the usefulness of the proposed system.