Semantic Cohesion for Image Annotation and Retrieval

Semantic Cohesion for Image Annotation and Retrieval

We present methods for image annotation and retrieval based on semantic cohesion among terms. On the one hand, we propose a region labeling technique that assigns an image the label that maximizes an estimate of semantic cohesion among candidate labels associated to regions in segmented images. On the other hand, we propose document representation techniques based on semantic cohesion among multimodal terms that compose images. We report experimental results that show the effectiveness of the proposed techniques. Additionally, we describe an extension of a benchmark collection for evaluation of the proposed techniques.

Saved in:
Bibliographic Details
Main Authors: Escalante,Hugo Jair, Sucar,Luis Enrique, Montes-y-Gómez,Manuel
Format: Digital revista
Language:English
Published: Instituto Politécnico Nacional, Centro de Investigación en Computación 2012
Online Access:http://www.scielo.org.mx/scielo.php?script=sci_arttext&pid=S1405-55462012000100011
Tags: Add Tag
No Tags, Be the first to tag this record!
id oai:scielo:S1405-55462012000100011
record_format ojs
spelling oai:scielo:S1405-554620120001000112013-06-11Semantic Cohesion for Image Annotation and RetrievalEscalante,Hugo JairSucar,Luis EnriqueMontes-y-Gómez,Manuel Automatic image annotation region labeling multimedia image retrieval ground truth data creation We present methods for image annotation and retrieval based on semantic cohesion among terms. On the one hand, we propose a region labeling technique that assigns an image the label that maximizes an estimate of semantic cohesion among candidate labels associated to regions in segmented images. On the other hand, we propose document representation techniques based on semantic cohesion among multimodal terms that compose images. We report experimental results that show the effectiveness of the proposed techniques. Additionally, we describe an extension of a benchmark collection for evaluation of the proposed techniques.info:eu-repo/semantics/openAccessInstituto Politécnico Nacional, Centro de Investigación en ComputaciónComputación y Sistemas v.16 n.1 20122012-03-01info:eu-repo/semantics/articletext/htmlhttp://www.scielo.org.mx/scielo.php?script=sci_arttext&pid=S1405-55462012000100011en
institution SCIELO
collection OJS
country México
countrycode MX
component Revista
access En linea
databasecode rev-scielo-mx
tag revista
region America del Norte
libraryname SciELO
language English
format Digital
author Escalante,Hugo Jair
Sucar,Luis Enrique
Montes-y-Gómez,Manuel
spellingShingle Escalante,Hugo Jair
Sucar,Luis Enrique
Montes-y-Gómez,Manuel
Semantic Cohesion for Image Annotation and Retrieval
author_facet Escalante,Hugo Jair
Sucar,Luis Enrique
Montes-y-Gómez,Manuel
author_sort Escalante,Hugo Jair
title Semantic Cohesion for Image Annotation and Retrieval
title_short Semantic Cohesion for Image Annotation and Retrieval
title_full Semantic Cohesion for Image Annotation and Retrieval
title_fullStr Semantic Cohesion for Image Annotation and Retrieval
title_full_unstemmed Semantic Cohesion for Image Annotation and Retrieval
title_sort semantic cohesion for image annotation and retrieval
description We present methods for image annotation and retrieval based on semantic cohesion among terms. On the one hand, we propose a region labeling technique that assigns an image the label that maximizes an estimate of semantic cohesion among candidate labels associated to regions in segmented images. On the other hand, we propose document representation techniques based on semantic cohesion among multimodal terms that compose images. We report experimental results that show the effectiveness of the proposed techniques. Additionally, we describe an extension of a benchmark collection for evaluation of the proposed techniques.
publisher Instituto Politécnico Nacional, Centro de Investigación en Computación
publishDate 2012
url http://www.scielo.org.mx/scielo.php?script=sci_arttext&pid=S1405-55462012000100011
work_keys_str_mv AT escalantehugojair semanticcohesionforimageannotationandretrieval
AT sucarluisenrique semanticcohesionforimageannotationandretrieval
AT montesygomezmanuel semanticcohesionforimageannotationandretrieval
_version_ 1756225736992096256

Similar Items