A novel complete face detection method in color images

Author

Zhao, Minghua ; Li, Peng ; Wang, Li

Author_Institution

Fac. of Comput. Sci. & Eng., Xi´´an Univ. of Technol., Xi´´an, China

Volume

4

fYear

2010

fDate

16-18 Oct. 2010

Firstpage

1763

Lastpage

1766

Abstract

A novel complete face detection method in color images based on facial characteristics is proposed in this paper. Firstly, the image to be detected is illumination-compensated and transferred from RGB to YCgCr color space. Secondly, Gaussian skin color model is established with 179221 skin pixels and skin color similarity image is obtained. Thirdly, a fast 2D Otsu method is used into skin color segmentation. Fourthly, the skin color segmentation results are processed by erosion operation, dilation operation, 8 neighborhoods connected component analysis, some limited conditions and Euler number. Finally, the eye information based on direction of the facial symmetry axis is considered and the final face region is determined.

Keywords

Gaussian processes; face recognition; image colour analysis; image segmentation; 179221 skin pixels; 2D Otsu method; Gaussian skin color model; RGB; dilation operation; erosion operation; face detection method; facial characteristics; facial symmetry axis; neighborhood connected component analysis; skin color segmentation; skin color similarity image; Face; Face detection; Image color analysis; Image segmentation; Mathematical model; Pixel; Skin; color space; eye detection; face detection; facial symmetry axis; skin color segmentation;

fLanguage

English

Publisher

ieee

Conference_Titel

Image and Signal Processing (CISP), 2010 3rd International Congress on

Conference_Location

Yantai

Print_ISBN

978-1-4244-6513-2

Type

conf

DOI

10.1109/CISP.2010.5647937

Filename

5647937