Morphological hat-transform scale spaces and their use in texture classification

Andrei C. Jalba; J.B.T.M. Roerdink; M.H.F. Wilkinson

doi:10.1109/ICIP.2003.1246965

Morphological hat-transform scale spaces and their use in texture classification

Andrei C. Jalba
, J.B.T.M. Roerdink
, M.H.F. Wilkinson

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

6 Citations (Scopus)

Abstract

In this paper we present a multiscale morphological method for use in texture classification. A connected operator similar to the morphological hat-transform is defined, and two scale-space representations are built. The most important features are extracted from the scale spaces by unsupervised cluster analysis, and the resulting pattern vectors provide the input of a decision tree classifier. We obtain 93.5 % correct classification for the Brodatz texture database.

Original language	English
Title of host publication	Proceedings of the 2003 International Conference on Image Processing (ICIP 2003)
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	329-332
Number of pages	4
ISBN (Print)	0-7803-7750-8
DOIs	https://doi.org/10.1109/ICIP.2003.1246965
Publication status	Published - 2003
Externally published	Yes
Event	10th IEEE International Conference on Image Processing (ICIP 2003) - Barcelona, Spain Duration: 14 Sept 2003 → 17 Sept 2003 Conference number: 10

Conference

Conference	10th IEEE International Conference on Image Processing (ICIP 2003)
Abbreviated title	ICIP 2003
Country/Territory	Spain
City	Barcelona
Period	14/09/03 → 17/09/03

Access to Document

10.1109/ICIP.2003.1246965

Cite this

@inproceedings{48dc6196f7b14bd081c20d2893fde5b3,

title = "Morphological hat-transform scale spaces and their use in texture classification",

abstract = "In this paper we present a multiscale morphological method for use in texture classification. A connected operator similar to the morphological hat-transform is defined, and two scale-space representations are built. The most important features are extracted from the scale spaces by unsupervised cluster analysis, and the resulting pattern vectors provide the input of a decision tree classifier. We obtain 93.5 \% correct classification for the Brodatz texture database.",

author = "Jalba, \{Andrei C.\} and J.B.T.M. Roerdink and M.H.F. Wilkinson",

year = "2003",

doi = "10.1109/ICIP.2003.1246965",

language = "English",

isbn = "0-7803-7750-8",

pages = "329--332",

booktitle = "Proceedings of the 2003 International Conference on Image Processing (ICIP 2003)",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "10th IEEE International Conference on Image Processing (ICIP 2003), ICIP 2003 ; Conference date: 14-09-2003 Through 17-09-2003",

}

Jalba, AC, Roerdink, JBTM & Wilkinson, MHF 2003, Morphological hat-transform scale spaces and their use in texture classification. in Proceedings of the 2003 International Conference on Image Processing (ICIP 2003) . Institute of Electrical and Electronics Engineers, Piscataway, pp. 329-332, 10th IEEE International Conference on Image Processing (ICIP 2003), Barcelona, Spain, 14/09/03. https://doi.org/10.1109/ICIP.2003.1246965

Morphological hat-transform scale spaces and their use in texture classification. / Jalba, Andrei C.; Roerdink, J.B.T.M.; Wilkinson, M.H.F.
Proceedings of the 2003 International Conference on Image Processing (ICIP 2003) . Piscataway: Institute of Electrical and Electronics Engineers, 2003. p. 329-332.

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

TY - GEN

T1 - Morphological hat-transform scale spaces and their use in texture classification

AU - Jalba, Andrei C.

AU - Roerdink, J.B.T.M.

AU - Wilkinson, M.H.F.

N1 - Conference code: 10

PY - 2003

Y1 - 2003

N2 - In this paper we present a multiscale morphological method for use in texture classification. A connected operator similar to the morphological hat-transform is defined, and two scale-space representations are built. The most important features are extracted from the scale spaces by unsupervised cluster analysis, and the resulting pattern vectors provide the input of a decision tree classifier. We obtain 93.5 % correct classification for the Brodatz texture database.

AB - In this paper we present a multiscale morphological method for use in texture classification. A connected operator similar to the morphological hat-transform is defined, and two scale-space representations are built. The most important features are extracted from the scale spaces by unsupervised cluster analysis, and the resulting pattern vectors provide the input of a decision tree classifier. We obtain 93.5 % correct classification for the Brodatz texture database.

U2 - 10.1109/ICIP.2003.1246965

DO - 10.1109/ICIP.2003.1246965

M3 - Conference contribution

SN - 0-7803-7750-8

SP - 329

EP - 332

BT - Proceedings of the 2003 International Conference on Image Processing (ICIP 2003)

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

T2 - 10th IEEE International Conference on Image Processing (ICIP 2003)

Y2 - 14 September 2003 through 17 September 2003

ER -

Morphological hat-transform scale spaces and their use in texture classification

Abstract

Conference

Access to Document

Fingerprint

Cite this