Labelling images with spreading activation theory

The overwhelming amounts of digital images on the Web and personal computers have triggered the requirement of an effective tool to retrieve images of interest using semantic concepts. Due to the semantic gap between low-level features of image content and its high-level conceptual meaning, however, the performances of many existing automatic image annotation algorithms are not so satisfactory. In this paper, a novel approach based on the cognitive science theory is proposed to improve the quality of annotation. The main idea is that tags of an image are considered as nodes within a semantic network and the relevance between each tag and the image is regulated using the spreading activation theory. After the spreading activation process finishes, each image tag will be appointed an appropriate values depending on its relations to other tags. Experimental results conducted on 50,000 Flickr image dataset demonstrate that the proposed scheme can effectively improve the performance of image annotation.