Fusion Of Global Shape And Local Features Using Multi Classifier Framework For Object Class Recognition

Object class recognition deals with the classification of individual objects to a certain class. In images of natural scenes, objects appear in a variety of poses and scales, with or without occlusion. Object class recognition typically involves the extraction, processing and analysis of visual feat...

Full description

Saved in:

Bibliographic Details
Main Author:	Manshor, Noridayu
Format:	Thesis
Language:	English
Published:	2013
Subjects:	QA75.5-76.95 Electronic computers Computer science
Online Access:	http://eprints.usm.my/43876/1/Noridayu%20Manshor24.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-usm-ep.43876
record_format	uketd_dc
spelling	my-usm-ep.438762019-04-12T05:26:10Z Fusion Of Global Shape And Local Features Using Multi Classifier Framework For Object Class Recognition 2013-10 Manshor, Noridayu QA75.5-76.95 Electronic computers. Computer science Object class recognition deals with the classification of individual objects to a certain class. In images of natural scenes, objects appear in a variety of poses and scales, with or without occlusion. Object class recognition typically involves the extraction, processing and analysis of visual features such as color, shape, or texture from an object, and then associating a class label to it. In this thesis, global shape and local features are considered as discriminative features for object class recognition. For local features, misclassification problems occur if the object is too small and possess weak local features. Besides that, local features do not give implicit importance to the shape of the object, which is one of important features to human vision. Detecting objects is difficult if the pose changes. Consequently, pose changes will result in changes in shape features for an object in the same class. Hence, both local and shape features are combined in order to obtain better classification performance for each object class. Ultimately, a meta-classifier framework is proposed as a model for object class recognition. Meta-classifier is used to learn a meta-classifier that optimally predicts the correctness of classification of base classifier for each object. In this framework, individual classifiers are trained using the local and global shape features, respectively. Then, these classifiers results are combined as input to the meta-classifier. Experimental results have shown to be comparable, or superior to existing state-of- the-art works for object class recognition. 2013-10 Thesis http://eprints.usm.my/43876/ http://eprints.usm.my/43876/1/Noridayu%20Manshor24.pdf application/pdf en public phd doctoral Universiti Sains Malaysia Pusat Pengajian Sains Komputer
institution	Universiti Sains Malaysia
collection	USM Institutional Repository
language	English
topic	QA75.5-76.95 Electronic computers Computer science
spellingShingle	QA75.5-76.95 Electronic computers Computer science Manshor, Noridayu Fusion Of Global Shape And Local Features Using Multi Classifier Framework For Object Class Recognition
description	Object class recognition deals with the classification of individual objects to a certain class. In images of natural scenes, objects appear in a variety of poses and scales, with or without occlusion. Object class recognition typically involves the extraction, processing and analysis of visual features such as color, shape, or texture from an object, and then associating a class label to it. In this thesis, global shape and local features are considered as discriminative features for object class recognition. For local features, misclassification problems occur if the object is too small and possess weak local features. Besides that, local features do not give implicit importance to the shape of the object, which is one of important features to human vision. Detecting objects is difficult if the pose changes. Consequently, pose changes will result in changes in shape features for an object in the same class. Hence, both local and shape features are combined in order to obtain better classification performance for each object class. Ultimately, a meta-classifier framework is proposed as a model for object class recognition. Meta-classifier is used to learn a meta-classifier that optimally predicts the correctness of classification of base classifier for each object. In this framework, individual classifiers are trained using the local and global shape features, respectively. Then, these classifiers results are combined as input to the meta-classifier. Experimental results have shown to be comparable, or superior to existing state-of- the-art works for object class recognition.
format	Thesis
qualification_name	Doctor of Philosophy (PhD.)
qualification_level	Doctorate
author	Manshor, Noridayu
author_facet	Manshor, Noridayu
author_sort	Manshor, Noridayu
title	Fusion Of Global Shape And Local Features Using Multi Classifier Framework For Object Class Recognition
title_short	Fusion Of Global Shape And Local Features Using Multi Classifier Framework For Object Class Recognition
title_full	Fusion Of Global Shape And Local Features Using Multi Classifier Framework For Object Class Recognition
title_fullStr	Fusion Of Global Shape And Local Features Using Multi Classifier Framework For Object Class Recognition
title_full_unstemmed	Fusion Of Global Shape And Local Features Using Multi Classifier Framework For Object Class Recognition
title_sort	fusion of global shape and local features using multi classifier framework for object class recognition
granting_institution	Universiti Sains Malaysia
granting_department	Pusat Pengajian Sains Komputer
publishDate	2013
url	http://eprints.usm.my/43876/1/Noridayu%20Manshor24.pdf
_version_	1747821294727987200

Fusion Of Global Shape And Local Features Using Multi Classifier Framework For Object Class Recognition

Similar Items