Illumination normalization and skin color validation for robust face detection

Sanghun Lee; Chulhee Lee

doi:10.2352/ISSN.2470-1173.2016.19.COIMG-176

Illumination normalization and skin color validation for robust face detection

Sanghun Lee, Chulhee Lee

Department of Electrical and Electronic Engineering

Research output: Contribution to journal › Conference article › peer-review

3 Citations (Scopus)

Abstract

The conventional Viola-Jones face detector may fail to detect faces under severe illumination conditions. The proposed method is based on the difference of Gaussian (DoG) that has been widely used to compensate for illumination effects. In the proposed method, we combine an original image and its DoG-filtered image, as a linear combination. This operation removed some illumination effects and improved face detection performance. Using the YCbCr color space, a skin color validation procedure was applied after face candidates were obtained using the proposed detector. Experiments using the Bao database showed that the proposed methods reduced over 50% of false positives.

Original language	English
Journal	IS and T International Symposium on Electronic Imaging Science and Technology
DOIs	https://doi.org/10.2352/ISSN.2470-1173.2016.19.COIMG-176
Publication status	Published - 2016
Event	Computational Imaging XIV 2016 - San Francisco, United States Duration: 2016 Feb 14 → 2016 Feb 18

Bibliographical note

Publisher Copyright:
© 2016 Society for Imaging Science and Technology.

All Science Journal Classification (ASJC) codes

Computer Graphics and Computer-Aided Design
Computer Science Applications
Human-Computer Interaction
Software
Electrical and Electronic Engineering
Atomic and Molecular Physics, and Optics

Access to Document

10.2352/ISSN.2470-1173.2016.19.COIMG-176

Cite this

@article{cd6de6324c764f5f9409ef145d336d1a,

title = "Illumination normalization and skin color validation for robust face detection",

abstract = "The conventional Viola-Jones face detector may fail to detect faces under severe illumination conditions. The proposed method is based on the difference of Gaussian (DoG) that has been widely used to compensate for illumination effects. In the proposed method, we combine an original image and its DoG-filtered image, as a linear combination. This operation removed some illumination effects and improved face detection performance. Using the YCbCr color space, a skin color validation procedure was applied after face candidates were obtained using the proposed detector. Experiments using the Bao database showed that the proposed methods reduced over 50% of false positives.",

author = "Sanghun Lee and Chulhee Lee",

note = "Publisher Copyright: {\textcopyright} 2016 Society for Imaging Science and Technology.; Computational Imaging XIV 2016 ; Conference date: 14-02-2016 Through 18-02-2016",

year = "2016",

doi = "10.2352/ISSN.2470-1173.2016.19.COIMG-176",

language = "English",

journal = "IS and T International Symposium on Electronic Imaging Science and Technology",

issn = "2470-1173",

}

TY - JOUR

T1 - Illumination normalization and skin color validation for robust face detection

AU - Lee, Sanghun

AU - Lee, Chulhee

PY - 2016

Y1 - 2016

N2 - The conventional Viola-Jones face detector may fail to detect faces under severe illumination conditions. The proposed method is based on the difference of Gaussian (DoG) that has been widely used to compensate for illumination effects. In the proposed method, we combine an original image and its DoG-filtered image, as a linear combination. This operation removed some illumination effects and improved face detection performance. Using the YCbCr color space, a skin color validation procedure was applied after face candidates were obtained using the proposed detector. Experiments using the Bao database showed that the proposed methods reduced over 50% of false positives.

AB - The conventional Viola-Jones face detector may fail to detect faces under severe illumination conditions. The proposed method is based on the difference of Gaussian (DoG) that has been widely used to compensate for illumination effects. In the proposed method, we combine an original image and its DoG-filtered image, as a linear combination. This operation removed some illumination effects and improved face detection performance. Using the YCbCr color space, a skin color validation procedure was applied after face candidates were obtained using the proposed detector. Experiments using the Bao database showed that the proposed methods reduced over 50% of false positives.

UR - http://www.scopus.com/inward/record.url?scp=85046055022&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046055022&partnerID=8YFLogxK

U2 - 10.2352/ISSN.2470-1173.2016.19.COIMG-176

DO - 10.2352/ISSN.2470-1173.2016.19.COIMG-176

M3 - Conference article

AN - SCOPUS:85046055022

SN - 2470-1173

JO - IS and T International Symposium on Electronic Imaging Science and Technology

JF - IS and T International Symposium on Electronic Imaging Science and Technology

T2 - Computational Imaging XIV 2016

Y2 - 14 February 2016 through 18 February 2016

ER -

Illumination normalization and skin color validation for robust face detection

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this