A Survey on Automatic Image Annotation and Trends of the New Age

With the rapid development of digital cameras, we have witnessed great interest and promise in automatic image annotation as a hot research field. Automatic image annotation could help to retrieval images in a large scale image database more rapidly and precisely. In this paper, different approaches of automatic annotation are reviewed:1) generative model based image annotation, 2) discriminative model based image annotation, 3) Graph model based image annotation. Several key theoretical and empirical contributions in the current decade related to automatic image annotation are discussed. Based on the analysis of what have been achieved in recent years, we believe that automatic image annotation will be paid more and more attentions in the near future.