Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/14471
Title: Fuzzy semantic labeling of natural images
Authors: PATERNO MARGARITA CARMEN SEMINIANO
Keywords: content-based image retrieval, semantic labeling, support vector machines
Issue Date: 25-Jan-2005
Source: PATERNO MARGARITA CARMEN SEMINIANO (2005-01-25). Fuzzy semantic labeling of natural images. ScholarBank@NUS Repository.
Abstract: This study proposes a fuzzy image labeling method that assigns multiple semanticlabels and associated confidence measures to an image block. The confidencemeasures are based on the orthogonal distance of the image blocka??s feature vector tothe hyperplane constructed by a Support Vector Machine (SVM). They are assignedto an image block to represent the signature of the image block, which, in regionmatching, is compared with prototype signatures representing different semanticclasses. Results of region classification tests with 31 semantic classes show that thefuzzy semantic labeling method yields higher classification accuracy and labelingeffectiveness than crisp labeling based on classification methods.
URI: http://scholarbank.nus.edu.sg/handle/10635/14471
Appears in Collections:Master's Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
mcsp_thesismanuscript_A4.pdf1.58 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

246
checked on Dec 11, 2017

Download(s)

190
checked on Dec 11, 2017

Google ScholarTM

Check


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