Cover Image

Ontology-based semantic image segmentation using mixture models and multiple CRFs

Semantic image segmentation is a fundamental yet challenging problem, which can be viewed as an extension of the conventional object detection with close relation to image segmentation and classification. It aims to partition images into non-overlapping regions that are assigned predefined semantic...

Full description

Saved in:
Bibliographic Details
Main Authors: Zand, Mohsen, Doraisamy, Shyamala, Abdul Halin, Alfian, Mustaffa, Mas Rina
Format: Article
Language:English
Published: Institute of Electrical and Electronics Engineers 2016
Online Access:http://psasir.upm.edu.my/id/eprint/53436/1/Ontology-based%20semantic%20image%20segmentation%20using%20mixture%20models%20and%20multiple%20CRFs.pdf
http://psasir.upm.edu.my/id/eprint/53436/
http://ieeexplore.ieee.org/document/7450190/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.upm.eprints.53436
record_format eprints
spelling my.upm.eprints.534362017-10-31T02:05:37Z http://psasir.upm.edu.my/id/eprint/53436/ Ontology-based semantic image segmentation using mixture models and multiple CRFs Zand, Mohsen Doraisamy, Shyamala Abdul Halin, Alfian Mustaffa, Mas Rina Semantic image segmentation is a fundamental yet challenging problem, which can be viewed as an extension of the conventional object detection with close relation to image segmentation and classification. It aims to partition images into non-overlapping regions that are assigned predefined semantic labels. Most of the existing approaches utilize and integrate low-level local features and high-level contextual cues, which are fed into an inference framework such as, the conditional random field (CRF). However, the lack of meaning in the primitives (i.e., pixels or superpixels) and the cues provides low discriminatory capabilities, since they are rarely object-consistent. Moreover, blind combinations of heterogeneous features and contextual cues exploitation through limited neighborhood relations in the CRFs tend to degrade the labeling performance. This paper proposes an ontology-based semantic image segmentation (OBSIS) approach that jointly models image segmentation and object detection. In particular, a Dirichlet process mixture model transforms the low-level visual space into an intermediate semantic space, which drastically reduces the feature dimensionality. These features are then individually weighed and independently learned within the context, using multiple CRFs. The segmentation of images into object parts is hence reduced to a classification task, where object inference is passed to an ontology model. This model resembles the way by which humans understand the images through the combination of different cues, context models, and rule-based learning of the ontologies. Experimental evaluations using the MSRC-21 and PASCAL VOC'2010 data sets show promising results. Institute of Electrical and Electronics Engineers 2016-07 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/53436/1/Ontology-based%20semantic%20image%20segmentation%20using%20mixture%20models%20and%20multiple%20CRFs.pdf Zand, Mohsen and Doraisamy, Shyamala and Abdul Halin, Alfian and Mustaffa, Mas Rina (2016) Ontology-based semantic image segmentation using mixture models and multiple CRFs. IEEE Transactions on Image Processing, 25 (7). pp. 3233-3248. ISSN 1057-7149, ESSN: 1941-0042 http://ieeexplore.ieee.org/document/7450190/ 10.1109/TIP.2016.2552401
institution Universiti Putra Malaysia
building UPM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Putra Malaysia
content_source UPM Institutional Repository
url_provider http://psasir.upm.edu.my/
language English
description Semantic image segmentation is a fundamental yet challenging problem, which can be viewed as an extension of the conventional object detection with close relation to image segmentation and classification. It aims to partition images into non-overlapping regions that are assigned predefined semantic labels. Most of the existing approaches utilize and integrate low-level local features and high-level contextual cues, which are fed into an inference framework such as, the conditional random field (CRF). However, the lack of meaning in the primitives (i.e., pixels or superpixels) and the cues provides low discriminatory capabilities, since they are rarely object-consistent. Moreover, blind combinations of heterogeneous features and contextual cues exploitation through limited neighborhood relations in the CRFs tend to degrade the labeling performance. This paper proposes an ontology-based semantic image segmentation (OBSIS) approach that jointly models image segmentation and object detection. In particular, a Dirichlet process mixture model transforms the low-level visual space into an intermediate semantic space, which drastically reduces the feature dimensionality. These features are then individually weighed and independently learned within the context, using multiple CRFs. The segmentation of images into object parts is hence reduced to a classification task, where object inference is passed to an ontology model. This model resembles the way by which humans understand the images through the combination of different cues, context models, and rule-based learning of the ontologies. Experimental evaluations using the MSRC-21 and PASCAL VOC'2010 data sets show promising results.
format Article
author Zand, Mohsen
Doraisamy, Shyamala
Abdul Halin, Alfian
Mustaffa, Mas Rina
spellingShingle Zand, Mohsen
Doraisamy, Shyamala
Abdul Halin, Alfian
Mustaffa, Mas Rina
Ontology-based semantic image segmentation using mixture models and multiple CRFs
author_facet Zand, Mohsen
Doraisamy, Shyamala
Abdul Halin, Alfian
Mustaffa, Mas Rina
author_sort Zand, Mohsen
title Ontology-based semantic image segmentation using mixture models and multiple CRFs
title_short Ontology-based semantic image segmentation using mixture models and multiple CRFs
title_full Ontology-based semantic image segmentation using mixture models and multiple CRFs
title_fullStr Ontology-based semantic image segmentation using mixture models and multiple CRFs
title_full_unstemmed Ontology-based semantic image segmentation using mixture models and multiple CRFs
title_sort ontology-based semantic image segmentation using mixture models and multiple crfs
publisher Institute of Electrical and Electronics Engineers
publishDate 2016
url http://psasir.upm.edu.my/id/eprint/53436/1/Ontology-based%20semantic%20image%20segmentation%20using%20mixture%20models%20and%20multiple%20CRFs.pdf
http://psasir.upm.edu.my/id/eprint/53436/
http://ieeexplore.ieee.org/document/7450190/
_version_ 1643835394716860416
score 13.211869

Similar Items