Evaluation of color representation for texture analysis

Abstract

Since more than 50 years texture in image material is a topic of research. Hereby, color was ignored mostly. This study compares 70 different configurations for texture analysis, using four features. For the configurations we used: (i) a gray value texture descriptor: the co-occurrence matrix and a color texture descriptor: the color correlogram, (ii) six color spaces, and (iii) several quantization schemes. A three classifier combination was used to classify the output of the configurations on the VisTex texture database. The results indicate that the use of a coarse HSV color space quantization can substantially improve texture recognition compared to various other gray and color quantization schemes.

Original language	English
Title of host publication	BNAIC'04
Subtitle of host publication	Proceedings of the 16th Belgium-Netherlands Conference on Artificial Intelligence, University of Groningen, 21-22 October, 2004
Editors	Rineke Verbrugge, Niels Taatgen, Lambert Schomaker
Place of Publication	Groningen
Publisher	University of Groningen
Pages	35-42
Number of pages	8
Publication status	Published - 2004
Event	16th Belgium-Dutch Conference on Artificial Intelligence, BNAIC 2004 - Groningen, Netherlands Duration: 21 Oct 2004 → 22 Oct 2004 Conference number: 16

Publication series

Name	BNAIC proceedings
Volume	16
ISSN (Print)	1568-7805

Conference

Conference	16th Belgium-Dutch Conference on Artificial Intelligence, BNAIC 2004
Abbreviated title	BNAIC
Country/Territory	Netherlands
City	Groningen
Period	21/10/04 → 22/10/04

Keywords

HMI-VRG: Virtual Reality and Graphics
HMI-HF: Human Factors
HMI-CI: Computational Intelligence
Co-occurence matrix
Color correlogram
Color
Pattern recognition
Texture
Classification
Evaluation

Access to Document

ArticleFinal published version, 380 KB

Cite this

van den Broek, E.L. ; van Rikxoort, E.M. / Evaluation of color representation for texture analysis. BNAIC'04: Proceedings of the 16th Belgium-Netherlands Conference on Artificial Intelligence, University of Groningen, 21-22 October, 2004. editor / Rineke Verbrugge ; Niels Taatgen ; Lambert Schomaker. Groningen : University of Groningen, 2004. pp. 35-42 (BNAIC proceedings).

@inproceedings{b3cab655ccfa45d3af08cf5994649789,

title = "Evaluation of color representation for texture analysis",

abstract = "Since more than 50 years texture in image material is a topic of research. Hereby, color was ignored mostly. This study compares 70 different configurations for texture analysis, using four features. For the configurations we used: (i) a gray value texture descriptor: the co-occurrence matrix and a color texture descriptor: the color correlogram, (ii) six color spaces, and (iii) several quantization schemes. A three classifier combination was used to classify the output of the configurations on the VisTex texture database. The results indicate that the use of a coarse HSV color space quantization can substantially improve texture recognition compared to various other gray and color quantization schemes.",

keywords = "HMI-VRG: Virtual Reality and Graphics, HMI-HF: Human Factors, HMI-CI: Computational Intelligence, Co-occurence matrix, Color correlogram, Color, Pattern recognition, Texture, Classification, Evaluation",

author = "{van den Broek}, E.L. and {van Rikxoort}, E.M.",

year = "2004",

language = "English",

series = "BNAIC proceedings",

publisher = "University of Groningen",

pages = "35--42",

editor = "Rineke Verbrugge and Niels Taatgen and Lambert Schomaker",

booktitle = "BNAIC'04",

note = "16th Belgium-Dutch Conference on Artificial Intelligence, BNAIC 2004, BNAIC ; Conference date: 21-10-2004 Through 22-10-2004",

}

van den Broek, EL & van Rikxoort, EM 2004, Evaluation of color representation for texture analysis. in R Verbrugge, N Taatgen & L Schomaker (eds), BNAIC'04: Proceedings of the 16th Belgium-Netherlands Conference on Artificial Intelligence, University of Groningen, 21-22 October, 2004. BNAIC proceedings, vol. 16, University of Groningen, Groningen, pp. 35-42, 16th Belgium-Dutch Conference on Artificial Intelligence, BNAIC 2004, Groningen, Netherlands, 21/10/04.

Evaluation of color representation for texture analysis. / van den Broek, E.L.; van Rikxoort, E.M.
BNAIC'04: Proceedings of the 16th Belgium-Netherlands Conference on Artificial Intelligence, University of Groningen, 21-22 October, 2004. ed. / Rineke Verbrugge; Niels Taatgen; Lambert Schomaker. Groningen: University of Groningen, 2004. p. 35-42 (BNAIC proceedings; Vol. 16).

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

TY - GEN

T1 - Evaluation of color representation for texture analysis

AU - van den Broek, E.L.

AU - van Rikxoort, E.M.

N1 - Conference code: 16

PY - 2004

Y1 - 2004

N2 - Since more than 50 years texture in image material is a topic of research. Hereby, color was ignored mostly. This study compares 70 different configurations for texture analysis, using four features. For the configurations we used: (i) a gray value texture descriptor: the co-occurrence matrix and a color texture descriptor: the color correlogram, (ii) six color spaces, and (iii) several quantization schemes. A three classifier combination was used to classify the output of the configurations on the VisTex texture database. The results indicate that the use of a coarse HSV color space quantization can substantially improve texture recognition compared to various other gray and color quantization schemes.

AB - Since more than 50 years texture in image material is a topic of research. Hereby, color was ignored mostly. This study compares 70 different configurations for texture analysis, using four features. For the configurations we used: (i) a gray value texture descriptor: the co-occurrence matrix and a color texture descriptor: the color correlogram, (ii) six color spaces, and (iii) several quantization schemes. A three classifier combination was used to classify the output of the configurations on the VisTex texture database. The results indicate that the use of a coarse HSV color space quantization can substantially improve texture recognition compared to various other gray and color quantization schemes.

KW - HMI-VRG: Virtual Reality and Graphics

KW - HMI-HF: Human Factors

KW - HMI-CI: Computational Intelligence

KW - Co-occurence matrix

KW - Color correlogram

KW - Color

KW - Pattern recognition

KW - Texture

KW - Classification

KW - Evaluation

M3 - Conference contribution

T3 - BNAIC proceedings

SP - 35

EP - 42

BT - BNAIC'04

A2 - Verbrugge, Rineke

A2 - Taatgen, Niels

A2 - Schomaker, Lambert

PB - University of Groningen

CY - Groningen

T2 - 16th Belgium-Dutch Conference on Artificial Intelligence, BNAIC 2004

Y2 - 21 October 2004 through 22 October 2004

ER -