Normalized colour segmentation for human appearance description

Robert Benavente; Gemma Sánchez; Ramon Baldrich; Maria Vanrell; Josep Lladós

Normalized colour segmentation for human appearance description

Robert Benavente, Gemma Sánchez, Ramon Baldrich, Maria Vanrell, Josep Lladós

Research output: Contribution to journal › Article › Research › peer-review

Abstract

In this paper we present a colour segmentation method based on a normalized colour naming algorithm which removes the effects of the varying conditions due to changes in scene illuminant. Images labelled with the colour name and intensity of small regions are further processed by a region growing step providing a sound segmentation. The method has been tested on a large set of images we get from a surveillance system, whose goal is the automatic retrieval of people from an image database using their appearance description. It is given in terms of placement of the colour regions in clothes. Finally, a quantitative measurement to evaluate the performance of the algorithm has been defined. © 2000 IEEE.

Original language	English
Pages (from-to)	633-637
Journal	Proceedings - International Conference on Pattern Recognition
Volume	15
Issue number	3
Publication status	Published - 1 Dec 2000

Keywords

Colour naming
Colour normalization
Performance evaluation
Region growing
Surveillance

Fingerprint Dive into the research topics of 'Normalized colour segmentation for human appearance description'. Together they form a unique fingerprint.

Cite this

@article{2824de16d64140a6bf42029814835829,

title = "Normalized colour segmentation for human appearance description",

abstract = "In this paper we present a colour segmentation method based on a normalized colour naming algorithm which removes the effects of the varying conditions due to changes in scene illuminant. Images labelled with the colour name and intensity of small regions are further processed by a region growing step providing a sound segmentation. The method has been tested on a large set of images we get from a surveillance system, whose goal is the automatic retrieval of people from an image database using their appearance description. It is given in terms of placement of the colour regions in clothes. Finally, a quantitative measurement to evaluate the performance of the algorithm has been defined. {\textcopyright} 2000 IEEE.",

keywords = "Colour naming, Colour normalization, Performance evaluation, Region growing, Surveillance",

author = "Robert Benavente and Gemma S{\'a}nchez and Ramon Baldrich and Maria Vanrell and Josep Llad{\'o}s",

year = "2000",

month = dec,

day = "1",

language = "English",

volume = "15",

pages = "633--637",

journal = "Proceedings - International Conference on Pattern Recognition",

issn = "1051-4651",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "3",

}

TY - JOUR

T1 - Normalized colour segmentation for human appearance description

AU - Benavente, Robert

AU - Sánchez, Gemma

AU - Baldrich, Ramon

AU - Vanrell, Maria

AU - Lladós, Josep

PY - 2000/12/1

Y1 - 2000/12/1

N2 - In this paper we present a colour segmentation method based on a normalized colour naming algorithm which removes the effects of the varying conditions due to changes in scene illuminant. Images labelled with the colour name and intensity of small regions are further processed by a region growing step providing a sound segmentation. The method has been tested on a large set of images we get from a surveillance system, whose goal is the automatic retrieval of people from an image database using their appearance description. It is given in terms of placement of the colour regions in clothes. Finally, a quantitative measurement to evaluate the performance of the algorithm has been defined. © 2000 IEEE.

AB - In this paper we present a colour segmentation method based on a normalized colour naming algorithm which removes the effects of the varying conditions due to changes in scene illuminant. Images labelled with the colour name and intensity of small regions are further processed by a region growing step providing a sound segmentation. The method has been tested on a large set of images we get from a surveillance system, whose goal is the automatic retrieval of people from an image database using their appearance description. It is given in terms of placement of the colour regions in clothes. Finally, a quantitative measurement to evaluate the performance of the algorithm has been defined. © 2000 IEEE.

KW - Colour naming

KW - Colour normalization

KW - Performance evaluation

KW - Region growing

KW - Surveillance

M3 - Article

VL - 15

SP - 633

EP - 637

JO - Proceedings - International Conference on Pattern Recognition

JF - Proceedings - International Conference on Pattern Recognition

SN - 1051-4651

IS - 3

ER -