Supervised Segmentation of Textures in Backscatter Images

P Paclik; RPW Duin; GMP van Kempen; R Kohlus

Supervised Segmentation of Textures in Backscatter Images

P Paclik, RPW Duin, GMP van Kempen, R Kohlus

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

15 Citations (Scopus)

Abstract

In this paper we present an application of statistical pattern recognition for segmentation of backscatter images (BSE) in product analysis of laundry detergents. Currently, application experts segment BSE images interactively which is both time consuming and expert dependent. We present a new, automatic, procedure for supervised BSE segmentation which is trained using additional multi-spectral EDX images. Each time a new feature selection procedure is employed to find a convenient feature subset for a particular segmentation problem. The performance of the presented algorithm is evaluated using ground-truth segmentation results. It is compared with that of interactive segmentation performed by the analyst.

Original language	Undefined/Unknown
Title of host publication	ICPR16, Proceedings
Editors	R Kasturi, D Laurendeau, C Suen
Place of Publication	Los Alamitos, CA
Publisher	IEEE
Pages	490-493
Number of pages	4
ISBN (Print)	0-7695-1696-3
Publication status	Published - 2002
Event	16th International Conference on Pattern Recognition (Quebec City, Canada), vol. II - Los Alamitos, CA Duration: 11 Aug 2002 → 15 Aug 2002

Publication series

Name
Publisher	IEEE Computer Society Press

Name	International Conference on Pattern Recognition
Volume	2
ISSN (Print)	1051-4651

Conference

Conference	16th International Conference on Pattern Recognition (Quebec City, Canada), vol. II
Period	11/08/02 → 15/08/02

Bibliographical note

ISSN 1051-4651, phpub 43

Keywords

conference contrib. refereed
Conf.proc. > 3 pag

Cite this

@inproceedings{909a9ea20f334ab9a40c1e625bbfe9e9,

title = "Supervised Segmentation of Textures in Backscatter Images",

abstract = "In this paper we present an application of statistical pattern recognition for segmentation of backscatter images (BSE) in product analysis of laundry detergents. Currently, application experts segment BSE images interactively which is both time consuming and expert dependent. We present a new, automatic, procedure for supervised BSE segmentation which is trained using additional multi-spectral EDX images. Each time a new feature selection procedure is employed to find a convenient feature subset for a particular segmentation problem. The performance of the presented algorithm is evaluated using ground-truth segmentation results. It is compared with that of interactive segmentation performed by the analyst.",

keywords = "conference contrib. refereed, Conf.proc. > 3 pag",

author = "P Paclik and RPW Duin and {van Kempen}, GMP and R Kohlus",

note = "ISSN 1051-4651, phpub 43; 16th International Conference on Pattern Recognition (Quebec City, Canada), vol. II ; Conference date: 11-08-2002 Through 15-08-2002",

year = "2002",

language = "Undefined/Unknown",

isbn = "0-7695-1696-3",

publisher = "IEEE",

pages = "490--493",

editor = "R Kasturi and D Laurendeau and C Suen",

booktitle = "ICPR16, Proceedings",

address = "United States",

}

Supervised Segmentation of Textures in Backscatter Images. / Paclik, P; Duin, RPW; van Kempen, GMP et al.
ICPR16, Proceedings. ed. / R Kasturi; D Laurendeau; C Suen. Los Alamitos, CA: IEEE, 2002. p. 490-493 (International Conference on Pattern Recognition; Vol. 2).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Supervised Segmentation of Textures in Backscatter Images

AU - Paclik, P

AU - Duin, RPW

AU - van Kempen, GMP

AU - Kohlus, R

N1 - ISSN 1051-4651, phpub 43

PY - 2002

Y1 - 2002

N2 - In this paper we present an application of statistical pattern recognition for segmentation of backscatter images (BSE) in product analysis of laundry detergents. Currently, application experts segment BSE images interactively which is both time consuming and expert dependent. We present a new, automatic, procedure for supervised BSE segmentation which is trained using additional multi-spectral EDX images. Each time a new feature selection procedure is employed to find a convenient feature subset for a particular segmentation problem. The performance of the presented algorithm is evaluated using ground-truth segmentation results. It is compared with that of interactive segmentation performed by the analyst.

AB - In this paper we present an application of statistical pattern recognition for segmentation of backscatter images (BSE) in product analysis of laundry detergents. Currently, application experts segment BSE images interactively which is both time consuming and expert dependent. We present a new, automatic, procedure for supervised BSE segmentation which is trained using additional multi-spectral EDX images. Each time a new feature selection procedure is employed to find a convenient feature subset for a particular segmentation problem. The performance of the presented algorithm is evaluated using ground-truth segmentation results. It is compared with that of interactive segmentation performed by the analyst.

KW - conference contrib. refereed

KW - Conf.proc. > 3 pag

UR - http://www.computer.org/proceedings/icpr/1695/volume2/169520490abs.htm

M3 - Conference contribution

SN - 0-7695-1696-3

SP - 490

EP - 493

BT - ICPR16, Proceedings

A2 - Kasturi, R

A2 - Laurendeau, D

A2 - Suen, C

PB - IEEE

CY - Los Alamitos, CA

T2 - 16th International Conference on Pattern Recognition (Quebec City, Canada), vol. II

Y2 - 11 August 2002 through 15 August 2002

ER -

Supervised Segmentation of Textures in Backscatter Images

Abstract

Publication series

Conference

Bibliographical note

Keywords

Other files and links

Cite this