Towards Semantic Clustering – A Brief Overview

Image clustering is an important technology which helps users to get hold of thelarge amount of online visual information, especially after the rapid growth of theWeb. This paper focuses on image clustering methods and their application inimage collection or online image repository. Current progress of image clusteringrelated to image retrieval and image annotation are summarized and some openproblems are discussed. Related works are summarized based on the problemsaddressed, which are image segmentation, compact representation of image set,search space reduction, and semantic gap. Issues are also identified in currentprogress and semantic clustering is conjectured to be the potential trend. Ourframework of semantic clustering as well as the main abstraction levels involvedis briefly discussed.