Texture based classification and segmentation of tissues using DT-CWT feature extraction methods

Dogu Baran Aydogan; Markus Hannula; Tuukka Arola; Jari Hyttinen; Prasun Dastidar

doi:10.1109/CBMS.2008.46

Texture based classification and segmentation of tissues using DT-CWT feature extraction methods

Dogu Baran Aydogan
, Markus Hannula
, Tuukka Arola
, Jari Hyttinen
, Prasun Dastidar

Not published at Aalto University

Tampere University of Technology
Tampere University

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

8 Citations (Scopus)

Abstract

In this study, four different dual-tree complex wavelet (DT-CWT) based texture feature extraction methods are developed and compared to segment and classify tissues. Methods that are proposed in this study are based on local energy calculations of sub-bands. Two of the methods use rotation variant texture features and the other two use rotation invariant features. The methods are tested on two texture compositions from the Brodatz texture database and two actual magnetic resonance (MR) images. Results show that there is not a significant difference between using rotation variant or invariant features. On the other hand, for the same Brodatz textures, all DT-CWT based feature extraction methods are competitive with other filtering approaches.

Original language	English
Title of host publication	Proceedings of the 21st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2008
Pages	614-619
Number of pages	6
DOIs	https://doi.org/10.1109/CBMS.2008.46
Publication status	Published - 22 Sept 2008
MoE publication type	A4 Conference publication
Event	IEEE International Symposium on Computer-Based Medical Systems - Jyväskylä, Finland Duration: 17 Jun 2008 → 19 Jun 2008 Conference number: 21

Conference

Conference	IEEE International Symposium on Computer-Based Medical Systems
Abbreviated title	CBMS
Country/Territory	Finland
City	Jyväskylä
Period	17/06/2008 → 19/06/2008

Access to Document

10.1109/CBMS.2008.46

Cite this

@inproceedings{40b396c7afb04899ba0a25d0533473c5,

title = "Texture based classification and segmentation of tissues using DT-CWT feature extraction methods",

abstract = "In this study, four different dual-tree complex wavelet (DT-CWT) based texture feature extraction methods are developed and compared to segment and classify tissues. Methods that are proposed in this study are based on local energy calculations of sub-bands. Two of the methods use rotation variant texture features and the other two use rotation invariant features. The methods are tested on two texture compositions from the Brodatz texture database and two actual magnetic resonance (MR) images. Results show that there is not a significant difference between using rotation variant or invariant features. On the other hand, for the same Brodatz textures, all DT-CWT based feature extraction methods are competitive with other filtering approaches.",

author = "Aydogan, \{Dogu Baran\} and Markus Hannula and Tuukka Arola and Jari Hyttinen and Prasun Dastidar",

year = "2008",

month = sep,

day = "22",

doi = "10.1109/CBMS.2008.46",

language = "English",

isbn = "9780769531656",

pages = "614--619",

booktitle = "Proceedings of the 21st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2008",

note = "IEEE International Symposium on Computer-Based Medical Systems, CBMS ; Conference date: 17-06-2008 Through 19-06-2008",

}

Aydogan, DB, Hannula, M, Arola, T, Hyttinen, J & Dastidar, P 2008, Texture based classification and segmentation of tissues using DT-CWT feature extraction methods. in Proceedings of the 21st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2008., 4562069, pp. 614-619, IEEE International Symposium on Computer-Based Medical Systems, Jyväskylä, Finland, 17/06/2008. https://doi.org/10.1109/CBMS.2008.46

Texture based classification and segmentation of tissues using DT-CWT feature extraction methods. / Aydogan, Dogu Baran; Hannula, Markus; Arola, Tuukka et al.
Proceedings of the 21st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2008. 2008. p. 614-619 4562069.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Texture based classification and segmentation of tissues using DT-CWT feature extraction methods

AU - Aydogan, Dogu Baran

AU - Hannula, Markus

AU - Arola, Tuukka

AU - Hyttinen, Jari

AU - Dastidar, Prasun

N1 - Conference code: 21

PY - 2008/9/22

Y1 - 2008/9/22

N2 - In this study, four different dual-tree complex wavelet (DT-CWT) based texture feature extraction methods are developed and compared to segment and classify tissues. Methods that are proposed in this study are based on local energy calculations of sub-bands. Two of the methods use rotation variant texture features and the other two use rotation invariant features. The methods are tested on two texture compositions from the Brodatz texture database and two actual magnetic resonance (MR) images. Results show that there is not a significant difference between using rotation variant or invariant features. On the other hand, for the same Brodatz textures, all DT-CWT based feature extraction methods are competitive with other filtering approaches.

AB - In this study, four different dual-tree complex wavelet (DT-CWT) based texture feature extraction methods are developed and compared to segment and classify tissues. Methods that are proposed in this study are based on local energy calculations of sub-bands. Two of the methods use rotation variant texture features and the other two use rotation invariant features. The methods are tested on two texture compositions from the Brodatz texture database and two actual magnetic resonance (MR) images. Results show that there is not a significant difference between using rotation variant or invariant features. On the other hand, for the same Brodatz textures, all DT-CWT based feature extraction methods are competitive with other filtering approaches.

UR - https://www.scopus.com/pages/publications/51849099089

U2 - 10.1109/CBMS.2008.46

DO - 10.1109/CBMS.2008.46

M3 - Conference article in proceedings

AN - SCOPUS:51849099089

SN - 9780769531656

SP - 614

EP - 619

BT - Proceedings of the 21st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2008

T2 - IEEE International Symposium on Computer-Based Medical Systems

Y2 - 17 June 2008 through 19 June 2008

ER -

Texture based classification and segmentation of tissues using DT-CWT feature extraction methods

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this