Proposed optimization for AdaBoost-based face detection

Jiu Xu; Satoshi Goto

doi:10.1117/12.896293

Proposed optimization for AdaBoost-based face detection

Jiu Xu^*, Satoshi Goto

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Citations (Scopus)

Abstract

In this paper, a novel approach is proposed for face detection in still image based on the AdaBoost algorithm. First, face candidates are detected by AdaBoost Algorithm. Since a lot of influence might exist, such as size of the image, illumination and noise, some non-faces windows might also be detected as face candidates, or some faces might be missed. In order to solve these problems and get better performances, we take use of skin color information in the YCbCr color space together with the edge information of the color image. In this way, we are able to remove some non-faces that have been wrongly detected as faces and add some possible missed faces as well. Experimental results show that the hit rate could be improved and false alarm could also be reduced by this method.

Original language	English
Title of host publication	Proceedings of SPIE - The International Society for Optical Engineering
Volume	8009
DOIs	https://doi.org/10.1117/12.896293
Publication status	Published - 2011
Event	3rd International Conference on Digital Image Processing, ICDIP 2011 - Chengdu Duration: 2011 Apr 15 → 2011 Apr 17

Other

Other	3rd International Conference on Digital Image Processing, ICDIP 2011
City	Chengdu
Period	11/4/15 → 11/4/17

Keywords

AdaBoost
canny edge detection
elliptical model
skin color segmentation

ASJC Scopus subject areas

Applied Mathematics
Computer Science Applications
Electrical and Electronic Engineering
Electronic, Optical and Magnetic Materials
Condensed Matter Physics

Access to Document

10.1117/12.896293

Cite this

@inproceedings{a98c297c017a42c294550fac5218683f,

title = "Proposed optimization for AdaBoost-based face detection",

abstract = "In this paper, a novel approach is proposed for face detection in still image based on the AdaBoost algorithm. First, face candidates are detected by AdaBoost Algorithm. Since a lot of influence might exist, such as size of the image, illumination and noise, some non-faces windows might also be detected as face candidates, or some faces might be missed. In order to solve these problems and get better performances, we take use of skin color information in the YCbCr color space together with the edge information of the color image. In this way, we are able to remove some non-faces that have been wrongly detected as faces and add some possible missed faces as well. Experimental results show that the hit rate could be improved and false alarm could also be reduced by this method.",

keywords = "AdaBoost, canny edge detection, elliptical model, skin color segmentation",

author = "Jiu Xu and Satoshi Goto",

year = "2011",

doi = "10.1117/12.896293",

language = "English",

isbn = "9780819485830",

volume = "8009",

booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

note = "3rd International Conference on Digital Image Processing, ICDIP 2011 ; Conference date: 15-04-2011 Through 17-04-2011",

}

TY - GEN

T1 - Proposed optimization for AdaBoost-based face detection

AU - Xu, Jiu

AU - Goto, Satoshi

PY - 2011

Y1 - 2011

N2 - In this paper, a novel approach is proposed for face detection in still image based on the AdaBoost algorithm. First, face candidates are detected by AdaBoost Algorithm. Since a lot of influence might exist, such as size of the image, illumination and noise, some non-faces windows might also be detected as face candidates, or some faces might be missed. In order to solve these problems and get better performances, we take use of skin color information in the YCbCr color space together with the edge information of the color image. In this way, we are able to remove some non-faces that have been wrongly detected as faces and add some possible missed faces as well. Experimental results show that the hit rate could be improved and false alarm could also be reduced by this method.

AB - In this paper, a novel approach is proposed for face detection in still image based on the AdaBoost algorithm. First, face candidates are detected by AdaBoost Algorithm. Since a lot of influence might exist, such as size of the image, illumination and noise, some non-faces windows might also be detected as face candidates, or some faces might be missed. In order to solve these problems and get better performances, we take use of skin color information in the YCbCr color space together with the edge information of the color image. In this way, we are able to remove some non-faces that have been wrongly detected as faces and add some possible missed faces as well. Experimental results show that the hit rate could be improved and false alarm could also be reduced by this method.

KW - AdaBoost

KW - canny edge detection

KW - elliptical model

KW - skin color segmentation

UR - http://www.scopus.com/inward/record.url?scp=79960864484&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79960864484&partnerID=8YFLogxK

U2 - 10.1117/12.896293

DO - 10.1117/12.896293

M3 - Conference contribution

AN - SCOPUS:79960864484

SN - 9780819485830

VL - 8009

BT - Proceedings of SPIE - The International Society for Optical Engineering

T2 - 3rd International Conference on Digital Image Processing, ICDIP 2011

Y2 - 15 April 2011 through 17 April 2011

ER -

Proposed optimization for AdaBoost-based face detection

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this