Please use this identifier to cite or link to this item:
Title: Intelligent iconic pictorial database system
Keywords: Iconic pictorial database, Spatial relation, Image representation, Similarity, Interactive, Retrieval
Issue Date: 21-Dec-2006
Citation: ZHOU XIAOMING (2006-12-21). Intelligent iconic pictorial database system. ScholarBank@NUS Repository.
Abstract: Similarity-based retrieval of images is an important task in many image database applications. A major class of usersa?? requests requires retrieving those images in the database that are spatially similar to the query image. In this thesis, we propose two spatial relation representations for iconic pictures, i.e. Intrinsic Orientation and Topological (IO&T) relation representation and Augmented Orientation Spatial Relation (AOSR) representation. Based on the proposed representations, we discuss some similarity measures for automatic picture matching and similarity retrieval in iconic image databases. Since similarity is a fuzzy concept for different users and applications, to improve the usability of a retrieval system, we involve users in the interactive retrieval process. Some indexing approaches and retrieval procedures are discussed to capture the subjective information hidden in individual usera??s feedback to fill the gap between the objective system and individual retrieval process.
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
ZhouXM.pdf1.58 MBAdobe PDF



Page view(s)

checked on Dec 16, 2018


checked on Dec 16, 2018

Google ScholarTM


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