Skin color segmentation based on improved 2-D Otsu and YCgCr color space

ZHAO Ming-hua; WANG Li; LI Peng

doi:10.3969/j.issn.1001-3806.2011.03.037

In order to deal with the disadvantages of fixed-threshold method in skin color segmentation, a new algorithm based on 2-D Otsu and YCgCr color space was proposed after analysis and comparison of different color spaces and skin color models. Firstly, the skin color sample images compensated with light were transferred from RGB to YCgCr color space and the 2-D Gaussian skin color model was established based on the 179221 skin pixels. Secondly, the image to be segmented was light compensated and transferred from RGB to YCgCr color space. Thirdly, skin color similarity degree was computed based on the 2-D Gaussian model and the skin color similarity image was obtained. Finally, an improved 2-D Otsu method was used into segmentation of the skin color similarity image. Theoretical analysis and experimental results show that the new skin color segmentation method is superior to the traditional methods based on a fixed-threshold in pertinence and anti-noise robustness.

Skin color segmentation based on improved 2-D Otsu and YCgCr color space

1. Faculty of Computer Science and Engineering, Xi'an University of Technology, Xi'an 710048, China

Received Date: 2010-06-30

Accepted Date: 2010-09-10

Available Online: 2011-05-25

Abstract: In order to deal with the disadvantages of fixed-threshold method in skin color segmentation, a new algorithm based on 2-D Otsu and YCgCr color space was proposed after analysis and comparison of different color spaces and skin color models. Firstly, the skin color sample images compensated with light were transferred from RGB to YCgCr color space and the 2-D Gaussian skin color model was established based on the 179221 skin pixels. Secondly, the image to be segmented was light compensated and transferred from RGB to YCgCr color space. Thirdly, skin color similarity degree was computed based on the 2-D Gaussian model and the skin color similarity image was obtained. Finally, an improved 2-D Otsu method was used into segmentation of the skin color similarity image. Theoretical analysis and experimental results show that the new skin color segmentation method is superior to the traditional methods based on a fixed-threshold in pertinence and anti-noise robustness.

HTML

Reference (17)

[1]	YANG M H,KRIEMAN D J,AHUJA N.Detecting faces in images:a survey [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(1):34-58.
[2]	ABUTALEB A S.Automatic thresholding of gray-level pictures using two dimensional entropy[J].Computer Vision,Graphics,and Image Processing,1989,47(1):22-32.
[3]	ZHOU M.Low SNR infrared weak target image segmentation algorithm[J].Laser & Infrared,2004,34(2):225-228(in Chinese).
[4]	DU G.Eye location method based on symmetry analysis and high-order fractal feature[J].Image Signal Processing,2006,153(1):11-16.
[5]	HSIEH I S,FAN K C,LIU C.A statistic approach to the detection of human faces in color nature scene [J].Pattern Recognition,2002,35(7):1583-1596.
[6]	TSAI C C,CHENG W C,TAUR J S.Face detection using eigenface and neural network[C] //2006 IEEE International Conference on System,Man and Cybernetics(SMC'06).Taipei,Taiwan,China:IEEE Computer Society,2006:4343-4347(in Chinese).
[7]	de DIOS J J,GARCIA N.Face detection based on a new color space YCgCr [C] //Proceedings of the 2003 International Conference on Image Processing (ICIP'03).Barcelona,Catalonia,Spain:IEEE Computer Society,2003:909-912.
[8]	KAKUMANU P,MAKROGIANNIS S,BOURBAKIS N.A survey of skin-color modeling and detection methods[J].Pattern Recognition,2007,40(3):1106-1122.
[9]	CHAI D,NGAN K N.Locating facial region of a head-and-shoulders color image[J].Proceedings of the 3rd.International Conference on Face & Gesture Recognition(FG'98).Nara,Japan:IEEE Computer Society,1998:124-129.
[10]	YANG M H,AHUJA N.Detecting human faces in color images[C] //Proceedings of the 1998 IEEE International Conference on Image Processing (ICIP'98).Chicago,Illinois,USA:IEEE Computer Society,1998:127-130.
[11]	YANG M H,AHUJA N.Gaussian mixture model for human skin color and its application in image and videodatabases[C] //Proceedings of SPIE:Conference on Storage and Retrieval for Image and Video Databases.San Jose,California,USA:International Society for Optical Engineering,1999:458-466.
[12]	XIA Y,ZHAO R C.A new thresholding algorithm using spacial information[J].Chinese Journal of Stereology and Image Analysis,2002,7(4):235-239(in Chinese).
[13]	WEZKA J S,ROSENFELD A.Histogram modification for threshold selection[J].IEEE Transactions on Systems Man,and Cybernetics,1979,9(1):38-52.
[14]	KIRBY R L,ROSENFELD A.A note on the use of gray level,local average gray level space as an aid in threshold selection[J].IEEE Transactions on Systems Man,and Cybernetics,1979,9(12):860-864.
[15]	CHANDA B,MAJUMDER D D.The note on the use of gray level co-occurrence matrix in threshold selection[J].Signal Processing,1988,15(2):149-167.
[16]	OTSU N.A threshold selection method from gray-level histogram[J].IEEE Transactions on Systems Man,and Cybernetics,1979,9(1):62-66.
[17]	ZHAO M H,YOU Zh Sh,YU J,et al.Pose robust face recognition based on CASPCM model[J].Laser Technology,2006,30(4):429-431(in Chinese).

Skin color segmentation based on improved 2-D Otsu and YCgCr color space

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Proportional views