Cluster-Based Vector-Attribute Filtering for CT and MRI Enhancement

Fred N. Kiwanuka; Michael H.F. Wilkinson

Cluster-Based Vector-Attribute Filtering for CT and MRI Enhancement

Fred N. Kiwanuka, Michael H.F. Wilkinson

Intelligent Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

1 Citation (Scopus)

148 Downloads (Pure)

Abstract

Morphological attribute filters modify images based on properties or attributes of connected components. Usually, attribute filtering is based on a scalar property which has relatively little discriminating power. Vector-attribute filtering allow better description of characteristic features for 2D images. In this paper, we extend vector attribute filtering by incorporating unsupervised pattern recognition, where connected components are clustered based on the similarity of feature vectors. We show that the performance of these new filters is better than those of scalar attribute filters in enhancement of objects in medical volumes.

Original language	English
Title of host publication	Proceedings of the 21st International Conference on Pattern Recognition, ICPR 2012
Publisher	IEEE (The Institute of Electrical and Electronics Engineers)
Pages	3112-3115
Number of pages	4
ISBN (Print)	978-4-9906441-0-9
Publication status	Published - 2012
Event	21st International Conference on Pattern Recognition - Tsukuba, Japan Duration: 11-Nov-2012 → 15-Nov-2012 http://www.icpr2012.org/

Conference

Conference	21st International Conference on Pattern Recognition
Abbreviated title	ICPR
Country/Territory	Japan
City	Tsukuba
Period	11/11/2012 → 15/11/2012
Internet address	http://www.icpr2012.org/

Access to Document

2012ProcICPRKiwanuka.pdfFinal publisher's version, 1.3 MB

Handle.net

Persistent link

Cite this

@inproceedings{1192f1a728f64163a2333404c42a5248,

title = "Cluster-Based Vector-Attribute Filtering for CT and MRI Enhancement",

abstract = "Morphological attribute filters modify images based on properties or attributes of connected components. Usually, attribute filtering is based on a scalar property which has relatively little discriminating power. Vector-attribute filtering allow better description of characteristic features for 2D images. In this paper, we extend vector attribute filtering by incorporating unsupervised pattern recognition, where connected components are clustered based on the similarity of feature vectors. We show that the performance of these new filters is better than those of scalar attribute filters in enhancement of objects in medical volumes.",

author = "Kiwanuka, {Fred N.} and Wilkinson, {Michael H.F.}",

note = "Relation: http://www.rug.nl/research/jbi/ Rights: University of Groningen, Johann Bernoulli Institute for Mathematics and Computer Science; 21st International Conference on Pattern Recognition, ICPR ; Conference date: 11-11-2012 Through 15-11-2012",

year = "2012",

language = "English",

isbn = "978-4-9906441-0-9",

pages = "3112--3115",

booktitle = "Proceedings of the 21st International Conference on Pattern Recognition, ICPR 2012",

publisher = "IEEE (The Institute of Electrical and Electronics Engineers)",

url = "http://www.icpr2012.org/",

}

Cluster-Based Vector-Attribute Filtering for CT and MRI Enhancement. / Kiwanuka, Fred N.; Wilkinson, Michael H.F.
Proceedings of the 21st International Conference on Pattern Recognition, ICPR 2012. IEEE (The Institute of Electrical and Electronics Engineers), 2012. p. 3112-3115.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Cluster-Based Vector-Attribute Filtering for CT and MRI Enhancement

AU - Kiwanuka, Fred N.

AU - Wilkinson, Michael H.F.

N1 - Relation: http://www.rug.nl/research/jbi/ Rights: University of Groningen, Johann Bernoulli Institute for Mathematics and Computer Science

PY - 2012

Y1 - 2012

N2 - Morphological attribute filters modify images based on properties or attributes of connected components. Usually, attribute filtering is based on a scalar property which has relatively little discriminating power. Vector-attribute filtering allow better description of characteristic features for 2D images. In this paper, we extend vector attribute filtering by incorporating unsupervised pattern recognition, where connected components are clustered based on the similarity of feature vectors. We show that the performance of these new filters is better than those of scalar attribute filters in enhancement of objects in medical volumes.

AB - Morphological attribute filters modify images based on properties or attributes of connected components. Usually, attribute filtering is based on a scalar property which has relatively little discriminating power. Vector-attribute filtering allow better description of characteristic features for 2D images. In this paper, we extend vector attribute filtering by incorporating unsupervised pattern recognition, where connected components are clustered based on the similarity of feature vectors. We show that the performance of these new filters is better than those of scalar attribute filters in enhancement of objects in medical volumes.

M3 - Conference contribution

SN - 978-4-9906441-0-9

SP - 3112

EP - 3115

BT - Proceedings of the 21st International Conference on Pattern Recognition, ICPR 2012

PB - IEEE (The Institute of Electrical and Electronics Engineers)

T2 - 21st International Conference on Pattern Recognition

Y2 - 11 November 2012 through 15 November 2012

ER -

Cluster-Based Vector-Attribute Filtering for CT and MRI Enhancement

Abstract

Conference

Access to Document

Handle.net

Fingerprint

Cite this