Abstract
This paper proposes a semantic-based video retrieval system that supports semantic-based retrieval of large-capacity video data in a mobile environment. The proposed system automatically extracts content information from video data and retrieves video data using an indexing agent. The indexing agent analyzes a user’s basic queries while extracting actual keywords from the queries. It then makes the meaning of key frame annotations more concrete through the use of dependence weight values. In addition, the indexing agent compares query images and database key frames through the use of the proposed binary-image histogram technique and retrieves the most similar key frame image that is displayed to the user. In the evaluation of a performance experiment, the proposed semantic-based video retrieval system shows higher retrieval performance than existing techniques in terms of scene retrieval from video data.KeywordsBinary ImageVideo DataRetrieval SchemeMobile ClientRetrieval AccuracyThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call