Image browsing for efficient image annotation

Image annotation is a work intensive and difficult task. Approaches for automatic image annotation are not sufficiently mature yet to be used in practise. In this paper, we show how an image database visualisation and browsing tool can be used for efficient and effective annotation of image databases. In contrast to other approaches, which typically present images in a linear fashion, we employ a visualisation where images are arranged so that visually similar images are located close to each other. Organisation on a grid layout prevents image overlap and hence contributes to a clear presentation. Large image databases are handled through a hierarchical storage structure where each image in the visualisation can correspond to a cluster of images that can be expanded by the user. Experimental results indicate that annotation can be performed faster on our proposed system.