For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
A Construction of a New Image Database System which Realizes Fully Automated Image Keyword Extraction
Jun YAMANE Masao SAKAUCHI
IEICE TRANSACTIONS on Information and Systems
Publication Date: 1993/10/25
Print ISSN: 0916-8532
Type of Manuscript: Special Section PAPER (Special Section on Machine Vision Applications)
image retrieval, image database, state transition model, recognition thesaurus, automated keyword extraction,
Full Text: PDF(749.7KB)>>
Recently, a flexible image database retrieval system where image keywords can be captured automatically is strongly required, in order to manage a practical number of image data successfully. However, image recognition/understanding technology level is not generally sufficient enough to achieve this requirement. In order to overcome this problem, a new type of image database framework is proposed in this paper. In the proposed system, image keywords are extracted in fully-automated fashion by the flexible and generalized image recognition system. Image keywords employed in this system are a collection of recognized objects in the image, where achieved recognition levels are allowed to be intermediate or imperfect. The concept of recognition thesaurus" has been introduced to manage these various abstraction level of kerwords successfully. As an embodiment of this concept, an experimental image database with various types of sports scenes has been implemented and various retrieval evaluations have been performed. Experimental results reveal the effectiveness of the proposed method.