Efficient tools for power annotation of visual contents

摘要

Techniques for content-based image or video retrieval are not mature enough to recognize visual semantic completely. Whereas retrieval based on color, size, texture and shape are within the state of the art, our investigations on human factor analysis indicate that it is necessary to use captions or text annotations that are associated with photos and videos in content access of visual data. In this paper, a framework for integration of textual and visual content searching mechanism is presented. The framework includes ontology-based semantic query expansion, database navigation in a conceptual hierarchy, and a computational model for degree of term similarity calculation. The proposed method is embedded and evaluated in our novel content-based image database system called PicDB#8482;.