In this paper, we propose a novel approach of image annotation by constructing a hierarchical mapping between lowlevel visual features and text features utilizing the relations within and across both visual features and text features. Moreover, we propose a novel annotation strategy that maximizes both the accuracy and the diversity of the generated annotation by generalizing or specifying the annotation in the corresponding annotation hierarchy. Experiments with 4500 scientific images from Royal Society of Chemistry journals show that the proposed annotation approach produces satisfactory results at different levels of annotations. Categories and Subject Descriptors H.4.8 [Image Processing and Computer Vision]: Scene Analysis object recognition; H.3.3 [Information Storage and Retrieval]: Information Retrieval search process General Terms Algorithm, Experiment, Performance Keywords Image Annotation, Hierarchical Relation, Feature Mapping
Qiankun Zhao, Prasenjit Mitra, C. Lee Giles