Face detection and tracking in color images using color centroids segmentation

Qieshi Zhang, Seiichiro Kamata, Jun Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

14 Citations (Scopus)

Abstract

Human face detection plays an important role in many application areas such as video surveillance, human computer interface, face recognition, face search and face image database management etc. In human face detection applications, face region usually form an inconsequential part of images. Consequently, preliminary segmentation of images into regions that contain "non-face" objects and regions that may contain "face" candidates can greatly accelerate the process of human face detection. Color information based methods take a great attention, because colors have obviously character and robust visual cue for detection. This paper proposed a new method based on RGB color centroids segmentation (CCS) for face detection. This paper include two parts, first part is color image thresholding based on CCS and the second part is face detection based on region growing and facial features structure character combined method. The experimental results show the ideal thresholding result and better than the result of other color space analysis based thresholding methods. Proposed method can conquer the influence of different background conditions, position, scale instance and orientation in images from several photo collections and database; the effect is also better than existing skin color segmentation based methods.

Original languageEnglish
Title of host publication2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008
Pages1008-1013
Number of pages6
DOIs
Publication statusPublished - 2008
Event2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008 - Bangkok
Duration: 2009 Feb 212009 Feb 26

Other

Other2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008
CityBangkok
Period09/2/2109/2/26

Fingerprint

Face recognition
Color
Databases
Skin Pigmentation
Interfaces (computer)
Skin
Cues

Keywords

  • Color centroids segmentation
  • Color image thresholding
  • Face detection

ASJC Scopus subject areas

  • Biotechnology
  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Zhang, Q., Kamata, S., & Zhang, J. (2008). Face detection and tracking in color images using color centroids segmentation. In 2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008 (pp. 1008-1013). [4913138] https://doi.org/10.1109/ROBIO.2009.4913138

Face detection and tracking in color images using color centroids segmentation. / Zhang, Qieshi; Kamata, Seiichiro; Zhang, Jun.

2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008. 2008. p. 1008-1013 4913138.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhang, Q, Kamata, S & Zhang, J 2008, Face detection and tracking in color images using color centroids segmentation. in 2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008., 4913138, pp. 1008-1013, 2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008, Bangkok, 09/2/21. https://doi.org/10.1109/ROBIO.2009.4913138
Zhang Q, Kamata S, Zhang J. Face detection and tracking in color images using color centroids segmentation. In 2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008. 2008. p. 1008-1013. 4913138 https://doi.org/10.1109/ROBIO.2009.4913138
Zhang, Qieshi ; Kamata, Seiichiro ; Zhang, Jun. / Face detection and tracking in color images using color centroids segmentation. 2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008. 2008. pp. 1008-1013
@inproceedings{4b0ccf3b49f3427db6400355781e1c7b,
title = "Face detection and tracking in color images using color centroids segmentation",
abstract = "Human face detection plays an important role in many application areas such as video surveillance, human computer interface, face recognition, face search and face image database management etc. In human face detection applications, face region usually form an inconsequential part of images. Consequently, preliminary segmentation of images into regions that contain {"}non-face{"} objects and regions that may contain {"}face{"} candidates can greatly accelerate the process of human face detection. Color information based methods take a great attention, because colors have obviously character and robust visual cue for detection. This paper proposed a new method based on RGB color centroids segmentation (CCS) for face detection. This paper include two parts, first part is color image thresholding based on CCS and the second part is face detection based on region growing and facial features structure character combined method. The experimental results show the ideal thresholding result and better than the result of other color space analysis based thresholding methods. Proposed method can conquer the influence of different background conditions, position, scale instance and orientation in images from several photo collections and database; the effect is also better than existing skin color segmentation based methods.",
keywords = "Color centroids segmentation, Color image thresholding, Face detection",
author = "Qieshi Zhang and Seiichiro Kamata and Jun Zhang",
year = "2008",
doi = "10.1109/ROBIO.2009.4913138",
language = "English",
isbn = "9781424426799",
pages = "1008--1013",
booktitle = "2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008",

}

TY - GEN

T1 - Face detection and tracking in color images using color centroids segmentation

AU - Zhang, Qieshi

AU - Kamata, Seiichiro

AU - Zhang, Jun

PY - 2008

Y1 - 2008

N2 - Human face detection plays an important role in many application areas such as video surveillance, human computer interface, face recognition, face search and face image database management etc. In human face detection applications, face region usually form an inconsequential part of images. Consequently, preliminary segmentation of images into regions that contain "non-face" objects and regions that may contain "face" candidates can greatly accelerate the process of human face detection. Color information based methods take a great attention, because colors have obviously character and robust visual cue for detection. This paper proposed a new method based on RGB color centroids segmentation (CCS) for face detection. This paper include two parts, first part is color image thresholding based on CCS and the second part is face detection based on region growing and facial features structure character combined method. The experimental results show the ideal thresholding result and better than the result of other color space analysis based thresholding methods. Proposed method can conquer the influence of different background conditions, position, scale instance and orientation in images from several photo collections and database; the effect is also better than existing skin color segmentation based methods.

AB - Human face detection plays an important role in many application areas such as video surveillance, human computer interface, face recognition, face search and face image database management etc. In human face detection applications, face region usually form an inconsequential part of images. Consequently, preliminary segmentation of images into regions that contain "non-face" objects and regions that may contain "face" candidates can greatly accelerate the process of human face detection. Color information based methods take a great attention, because colors have obviously character and robust visual cue for detection. This paper proposed a new method based on RGB color centroids segmentation (CCS) for face detection. This paper include two parts, first part is color image thresholding based on CCS and the second part is face detection based on region growing and facial features structure character combined method. The experimental results show the ideal thresholding result and better than the result of other color space analysis based thresholding methods. Proposed method can conquer the influence of different background conditions, position, scale instance and orientation in images from several photo collections and database; the effect is also better than existing skin color segmentation based methods.

KW - Color centroids segmentation

KW - Color image thresholding

KW - Face detection

UR - http://www.scopus.com/inward/record.url?scp=70349186183&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70349186183&partnerID=8YFLogxK

U2 - 10.1109/ROBIO.2009.4913138

DO - 10.1109/ROBIO.2009.4913138

M3 - Conference contribution

AN - SCOPUS:70349186183

SN - 9781424426799

SP - 1008

EP - 1013

BT - 2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008

ER -