Conceptualization and ontology: tools for efficient storage and retrieveal of semantic visual information

摘要

Techniques for content-based image or video retrieval are not mature enough to recognize visual semantic completely. Retrieval based on color, size, texture and shape are within the state of the art. Our experiments on human factors in visual information query and retrieval show that visual information retrieval based on the semantic understanding of visual objects and content are more demanding rather than viual appearance based retrievel. Therefore, it is necessary to use captions or text annotations to photos or videos in content access of visual data.