Content based image and video retrieval using the QuickLook search engine
| Autor: | Gianluigi Ciocca, Isabella Gagliardi, Raimondo Schettini |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2004 |
| Předmět: | |
| Zdroj: | MultiMedia Information Retrieval: Metodologie ed esperienze internazionali di content-based retrieval per l'informazione e la documentazione, edited by Roberto Raieli Perla Innocenti ; premessa di Lucia Maffei, pp. 151–168, 2004 info:cnr-pdr/source/autori:Gianluigi Ciocca; Isabella Gagliardi; Raimondo Schettini/titolo:Content based image and video retrieval using the QuickLook search engine/titolo_volume:MultiMedia Information Retrieval: Metodologie ed esperienze internazionali di content-based retrieval per l'informazione e la documentazione/curatori_volume:Roberto Raieli Perla Innocenti ; premessa di Lucia Maffei/editore:/anno:2004 |
| Popis: | This paper describes the main features of QuickLook, a system that combines within a single framework the capabilities of alphanumeric relational query, the content-based image and video query exploiting automatically computed image features, and the textual similarity query using any textual annotations attached to database items (such as figure and video captions). The system offers the user several retrieval strategies for querying the database. He can then progressively refine the system's response by indicating the relevance, or non-relevance of the items retrieved. Once a subset of images meeting the user's information needs have been identified, these images can be displayed in a pseudo-3D virtual exhibition which the user can visit interactively by applying VRML technology. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|