3D head pose estimation using color information

Author

Chen, Qian ; Wu, Haiyuan ; Shioyama, Tadayosi ; Shimada, Tetsuo

Author_Institution

Fac. of Syst. Eng., Wakayama Univ., Japan

Volume

1

fYear

1999

fDate

36342

Firstpage

697

Abstract

This paper presents a new method to estimate the 3D pose of human heads in a single image. In contrast with other approaches, this method only uses color information about the skin region and the hair region of a head. We use an efficient algorithm based on a perceptually uniform color system and fuzzy theory to extract the skin region and the hair region, and to detect faces in images. After that, some geometrical properties such as the area, the center, and the axis of least inertia of the skin region and the hair region are calculated, which are then used to estimate the 3D pose of the head

Keywords

face recognition; fuzzy logic; image colour analysis; image segmentation; 3D head pose estimation; color information; face detection; face recognition; fuzzy theory; geometrical properties; hair region; perceptually uniform color system; skin region; three dimensional head pose estimation; Cameras; Data mining; Face detection; Face recognition; Facial features; Hair; Head; Neck; Skin; Systems engineering and theory;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia Computing and Systems, 1999. IEEE International Conference on

Conference_Location

Florence

Print_ISBN

0-7695-0253-9

Type

conf

DOI

10.1109/MMCS.1999.779284

Filename

779284