Staff View: An analysis of object appearance information and context based classification

An analysis of object appearance information and context based classification

The purpose of categorizing objects is to identify and locate within an image, instances of an object category. It is a difficult task to identify objects in images when such images contain poor quality, occlusion, background clutter, or noise. It is more difficult when there are too many objects in...

Full description

Saved in:

Bibliographic Details
Main Authors:	Katuka, Jatau Isaac, Mohammad, Dzulkifli, Saba, Tanzial, El-Affendi, Mohammad, Mohamed, Ahmed Sameh
Format:	Article
Published:	3D Display Research Center 2014
Subjects:	QA75 Electronic computers. Computer science
Online Access:	http://eprints.utm.my/id/eprint/51765/ http://dx.doi.org/10.1007/s13319-014-0024-5
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.utm.51765
record_format	eprints
spelling	my.utm.517652018-10-22T02:53:15Z http://eprints.utm.my/id/eprint/51765/ An analysis of object appearance information and context based classification Katuka, Jatau Isaac Mohammad, Dzulkifli Saba, Tanzial El-Affendi, Mohammad Mohamed, Ahmed Sameh QA75 Electronic computers. Computer science The purpose of categorizing objects is to identify and locate within an image, instances of an object category. It is a difficult task to identify objects in images when such images contain poor quality, occlusion, background clutter, or noise. It is more difficult when there are too many objects in same scene (background). Most models for categorizing object exploit context information and appearance information from objects in order to enhance recognition accuracy. In the scene, interaction among objects (context information) can successfully help in removing ambiguity of appearance inputs during recognition task. Appearance information can help identify object classes successfully up to some level. The issue of integrating several kinds of contextual information in order to have a robust categorization of object is address in this paper. Various methods of exploiting contextual information for categorizing object are review 3D Display Research Center 2014 Article PeerReviewed Katuka, Jatau Isaac and Mohammad, Dzulkifli and Saba, Tanzial and El-Affendi, Mohammad and Mohamed, Ahmed Sameh (2014) An analysis of object appearance information and context based classification. 3D Research, 5 (3). ISSN 2092-6731 http://dx.doi.org/10.1007/s13319-014-0024-5
institution	Universiti Teknologi Malaysia
building	UTM Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Teknologi Malaysia
content_source	UTM Institutional Repository
url_provider	http://eprints.utm.my/
topic	QA75 Electronic computers. Computer science
spellingShingle	QA75 Electronic computers. Computer science Katuka, Jatau Isaac Mohammad, Dzulkifli Saba, Tanzial El-Affendi, Mohammad Mohamed, Ahmed Sameh An analysis of object appearance information and context based classification
description	The purpose of categorizing objects is to identify and locate within an image, instances of an object category. It is a difficult task to identify objects in images when such images contain poor quality, occlusion, background clutter, or noise. It is more difficult when there are too many objects in same scene (background). Most models for categorizing object exploit context information and appearance information from objects in order to enhance recognition accuracy. In the scene, interaction among objects (context information) can successfully help in removing ambiguity of appearance inputs during recognition task. Appearance information can help identify object classes successfully up to some level. The issue of integrating several kinds of contextual information in order to have a robust categorization of object is address in this paper. Various methods of exploiting contextual information for categorizing object are review
format	Article
author	Katuka, Jatau Isaac Mohammad, Dzulkifli Saba, Tanzial El-Affendi, Mohammad Mohamed, Ahmed Sameh
author_facet	Katuka, Jatau Isaac Mohammad, Dzulkifli Saba, Tanzial El-Affendi, Mohammad Mohamed, Ahmed Sameh
author_sort	Katuka, Jatau Isaac
title	An analysis of object appearance information and context based classification
title_short	An analysis of object appearance information and context based classification
title_full	An analysis of object appearance information and context based classification
title_fullStr	An analysis of object appearance information and context based classification
title_full_unstemmed	An analysis of object appearance information and context based classification
title_sort	analysis of object appearance information and context based classification
publisher	3D Display Research Center
publishDate	2014
url	http://eprints.utm.my/id/eprint/51765/ http://dx.doi.org/10.1007/s13319-014-0024-5
_version_	1643653066081173504
score	13.211869

An analysis of object appearance information and context based classification

Similar Items