Content-Based retrieval supporting similarity query

We suggests a Hybrid Video Information System(HVIS) which supports the semantic retrieval of all the various users and the similarity retrieval of indefinite formed and great capacious video data. The HVIS divides a set of video into and suggests a Three layered Hybrid Objec video document, sequences, scenes and objects to model the metadata t-oriented Metadata Model (THOMM) which is composed of the raw-data layer for physical video stream. the metadata layer to support the feature-based retrieval and the similarity retrieval and the semantic layer to reform the query. Grounded on this model, we suggests the video query language which make content-based query and similarity query possible and Video Orrery Processor (VQP) to process the query. Specially the similarity query processed by performing the annotation-based retrieval using the concept layeer and then the feature-based retrieval using the objective-feature layer. Thus search space and time can be reduced. Also we present the formula for degree of similarity. The user can query; and can receive the result over Internet The suggested system is implemented with using the Visual C++, ActiveX and ORACLE render Windows NT.