Adaptive Skin Color Model Switching for Face Tracking under Varying Illumination

Author

Huang, Deng-Yuan ; Hu, Wu-Chih ; Hsu, Mao-Hsiang

Author_Institution

Dept. of Electr. Eng., Da-Yeh Univ., Changhua, Taiwan

fYear

2009

fDate

7-9 Dec. 2009

Firstpage

326

Lastpage

329

Abstract

In this paper, an adaptive skin color model switching based on AdaBoost method for face tracking is proposed. Possible skin clusters under illumination varying scenes are detected by an optimal skin color model, which is adaptively selected by a well-defined quality measure. The possible facial candidates are further validated by AdaBoost to determine whether human faces exist in video sequences or not. The tracking sequences reveal that good and robust results are obtained from dim-to profile-to back-light scenarios. The performance of the proposed method can achieve an average tracking time of about 145.4 ms/frame and a detection rate of 94.4%.

Keywords

image colour analysis; image sequences; learning (artificial intelligence); tracking; AdaBoost method; adaptive skin color model switching; face tracking sequence; illumination varying scene detection; skin clusters; video sequences; Classification algorithms; Cryptography; Feature extraction; Lighting; Skin; Steganography; Support vector machine classification; Support vector machines; Testing; Wavelet packets;

fLanguage

English

Publisher

ieee

Conference_Titel

Innovative Computing, Information and Control (ICICIC), 2009 Fourth International Conference on

Conference_Location

Kaohsiung

Print_ISBN

978-1-4244-5543-0

Type

conf

DOI

10.1109/ICICIC.2009.71

Filename

5412267