Please use this identifier to cite or link to this item: http://hdl.handle.net/2067/440
Title: Structured Knowledge Representation for Image Retrieval
Authors: Di Sciascio, Eugenio
Donini, Francesco Maria
Mongiello, Marina
Keywords: Image Retrieval;Knowledge Representation;Artificial Intelligence;Intelligent Systems
Issue Date: Apr-2002
Publisher: AI Access Foundation and Morgan Kaufmann Publishers
Source: Journal of Artificial Intelligence Research 16 (2002) 209-257
Abstract: 
We propose a structured approach to the problem of retrieval of images by content and present a description logic that has been devised for the semantic indexing and retrieval of images containing complex objects. As other approaches do, we start from low-level features extracted with image analysis to detect and characterize regions in an image. However, in contrast with feature-based approaches, we provide a syntax to describe segmented regions as basic objects and complex objects as compositions of basic ones. Then we introduce a companion extensional semantics for defining reasoning services, such as retrieval, classification, and subsumption. These services can be used for both exact and approximate matching, using similarity measures. Using our logical approach as a formal specification, we implemented a complete clientserver image retrieval system, which allows a user to pose both queries by sketch and queries by example. A set of experiments has been carried out on a testbed of images to assess the retrieval capabilities of the system in comparison with expert users ranking. Results are presented adopting a well-established measure of quality borrowed from textual information retrieval.
URI: http://hdl.handle.net/2067/440
ISSN: 11076 - 9757
Appears in Collections:DISUCOM - Archivio della produzione scientifica

Files in This Item:
File Description SizeFormat
2002-jair.pdf1.05 MBAdobe PDFView/Open
Show full item record

Page view(s)

1
Last Week
0
Last month
0
checked on Oct 20, 2020

Download(s)

2
checked on Oct 20, 2020

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.