Face detection in color images based on skin color models

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

10 Citations (Scopus)

Abstract

Face finding is a very important initial step towards building up a fully automated face recognition system. Face detection by detecting skin like colors can achieve a high detection rate. In this paper, we presented a novel algorithm for face detection in color images with complex backgrounds. First a parallel structure for skin color detection is proposed to improve the accuracy of detections. The concept of the probability image has been introduced to utilize the color information in the traditional face detection methods specific for gray-scale images. After that, a classifier obtained from Adaboost training is applied to the result of skin detection to reduce the false positives. An experiment has been implemented to verify the improvement of this proposed research. And the proposed approach achieved a better result in this experiment.

Original languageEnglish
Title of host publicationIEEE Region 10 Annual International Conference, Proceedings/TENCON
Pages681-686
Number of pages6
DOIs
Publication statusPublished - 2010
Event2010 IEEE Region 10 Conference, TENCON 2010 - Fukuoka
Duration: 2010 Nov 212010 Nov 24

Other

Other2010 IEEE Region 10 Conference, TENCON 2010
CityFukuoka
Period10/11/2110/11/24

Fingerprint

Face recognition
Skin
Color
Adaptive boosting
Classifiers
Experiments

Keywords

  • Adaboost
  • Face detection
  • Face skin categorization
  • GMM
  • Skin color

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications

Cite this

Zou, L., & Kamata, S. (2010). Face detection in color images based on skin color models. In IEEE Region 10 Annual International Conference, Proceedings/TENCON (pp. 681-686). [5686631] https://doi.org/10.1109/TENCON.2010.5686631

Face detection in color images based on skin color models. / Zou, Li; Kamata, Seiichiro.

IEEE Region 10 Annual International Conference, Proceedings/TENCON. 2010. p. 681-686 5686631.

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

Zou, L & Kamata, S 2010, Face detection in color images based on skin color models. in IEEE Region 10 Annual International Conference, Proceedings/TENCON., 5686631, pp. 681-686, 2010 IEEE Region 10 Conference, TENCON 2010, Fukuoka, 10/11/21. https://doi.org/10.1109/TENCON.2010.5686631
Zou L, Kamata S. Face detection in color images based on skin color models. In IEEE Region 10 Annual International Conference, Proceedings/TENCON. 2010. p. 681-686. 5686631 https://doi.org/10.1109/TENCON.2010.5686631
Zou, Li ; Kamata, Seiichiro. / Face detection in color images based on skin color models. IEEE Region 10 Annual International Conference, Proceedings/TENCON. 2010. pp. 681-686
@inproceedings{ad1aad182cd44d41b19c7f4729082277,
title = "Face detection in color images based on skin color models",
abstract = "Face finding is a very important initial step towards building up a fully automated face recognition system. Face detection by detecting skin like colors can achieve a high detection rate. In this paper, we presented a novel algorithm for face detection in color images with complex backgrounds. First a parallel structure for skin color detection is proposed to improve the accuracy of detections. The concept of the probability image has been introduced to utilize the color information in the traditional face detection methods specific for gray-scale images. After that, a classifier obtained from Adaboost training is applied to the result of skin detection to reduce the false positives. An experiment has been implemented to verify the improvement of this proposed research. And the proposed approach achieved a better result in this experiment.",
keywords = "Adaboost, Face detection, Face skin categorization, GMM, Skin color",
author = "Li Zou and Seiichiro Kamata",
year = "2010",
doi = "10.1109/TENCON.2010.5686631",
language = "English",
isbn = "9781424468904",
pages = "681--686",
booktitle = "IEEE Region 10 Annual International Conference, Proceedings/TENCON",

}

TY - GEN

T1 - Face detection in color images based on skin color models

AU - Zou, Li

AU - Kamata, Seiichiro

PY - 2010

Y1 - 2010

N2 - Face finding is a very important initial step towards building up a fully automated face recognition system. Face detection by detecting skin like colors can achieve a high detection rate. In this paper, we presented a novel algorithm for face detection in color images with complex backgrounds. First a parallel structure for skin color detection is proposed to improve the accuracy of detections. The concept of the probability image has been introduced to utilize the color information in the traditional face detection methods specific for gray-scale images. After that, a classifier obtained from Adaboost training is applied to the result of skin detection to reduce the false positives. An experiment has been implemented to verify the improvement of this proposed research. And the proposed approach achieved a better result in this experiment.

AB - Face finding is a very important initial step towards building up a fully automated face recognition system. Face detection by detecting skin like colors can achieve a high detection rate. In this paper, we presented a novel algorithm for face detection in color images with complex backgrounds. First a parallel structure for skin color detection is proposed to improve the accuracy of detections. The concept of the probability image has been introduced to utilize the color information in the traditional face detection methods specific for gray-scale images. After that, a classifier obtained from Adaboost training is applied to the result of skin detection to reduce the false positives. An experiment has been implemented to verify the improvement of this proposed research. And the proposed approach achieved a better result in this experiment.

KW - Adaboost

KW - Face detection

KW - Face skin categorization

KW - GMM

KW - Skin color

UR - http://www.scopus.com/inward/record.url?scp=79951615530&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79951615530&partnerID=8YFLogxK

U2 - 10.1109/TENCON.2010.5686631

DO - 10.1109/TENCON.2010.5686631

M3 - Conference contribution

SN - 9781424468904

SP - 681

EP - 686

BT - IEEE Region 10 Annual International Conference, Proceedings/TENCON

ER -