Detecting human faces in color images

Author

Cai, J. ; Goshtasby, A. ; Yu, C.

Author_Institution

Dept. of Comput. Sci. & Eng., Wright State Univ., Dayton, OH, USA

fYear

1998

fDate

5-7 Aug 1998

Firstpage

124

Lastpage

131

Abstract

A method is introduced that detects human faces in color images by first separating skin regions from non-skin regions and then locating faces within the skin regions. A chroma chart is prepared via a training process that shows likelihoods of different colors representing the skin. Using the chroma chart, a color image is transformed into a gray-scale image, with the gray value at a pixel showing the likelihood of the pixel representing the skin. By segmenting the gray-scale image, skin regions are separated from non-skin regions. Then, using the luminance component of the color image and by template matching, faces are located within skin regions

Keywords

brightness; face recognition; image colour analysis; image matching; image segmentation; learning (artificial intelligence); skin; chroma chart; color images; color likelihoods; gray-scale image; human face detection; image segmentation; luminance; skin region separation; template matching; training process; Color; Computer vision; Face detection; Facial features; Humans; Image edge detection; Image segmentation; Neural networks; Pixel; Skin;

fLanguage

English

Publisher

ieee

Conference_Titel

Multi-Media Database Management Systems, 1998. Proceedings. International Workshop on

Conference_Location

Dayton, OH

Print_ISBN

0-8186-8676-6

Type

conf

DOI

10.1109/MMDBMS.1998.709526

Filename

709526