Anzeige
Erschienen in:
2012 | OriginalPaper | Buchkapitel
A Scheme of Fragment-Based Faceted Image Search
verfasst von : Takahiro Komamizu, Mariko Kamie, Kazuhiro Fukui, Toshiyuki Amagasa, Hiroyuki Kitagawa
Erschienen in: Database and Expert Systems Applications
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Retrieving desired images from large amounts of images has been increasingly important. Traditionally keyword search and content-based image retrieval have been used for image search. However, such retrieval methods have scarcely assumed a case when users have few terms for desired images or few images similar to the desired images. For this problem, we use
fragments
of images extracted from datasets as values of facets in faceted navigation. We extract parts of images as fragments. Then, we make a several number of groups for each part to decide representative images for faceted navigation. Our empirical user study based on an example application using face image data, FUKUWARAI, shows that our proposal successfully supports users to find desired images.