IEICE TRANSACTIONS on Information
Facial Region Detection Using Range Color Information
Summary :
This paper proposes an object oriented face region detection and tracking method using range color information. Range segmentation of the objects are obtained from the complicated background using disparity histogram (DH). The facial regions among the range segmented objects are detected using skin-color transform technique that provides a facial region enhanced gray-level image. Computationally efficient matching pixel count (MPC) disparity measure is introduced to enhance the matching accuracy by removing the effect of the unexpected noise in the boundary region. Redundancy operations inherent in the area-based matching operation are removed to enhance the processing speed. For the skin-color transformation, the generalized facial color distribution (GFCD) is modeled by 2D Gaussian function in a normalized color space. Disparity difference histogram (DDH) concept from two consecutive frames is introduced to estimate the range information effectively. Detailed geometrical analysis provides exact variation of range information of moving object. The experimental results show that the proposed algorithm works well in various environments, at a rate of 1 frame per second with 512
- Publication
- IEICE TRANSACTIONS on Information Vol.E81-D No.9 pp.968-975
- Publication Date
- 1998/09/25
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- Special Section PAPER (Special Issue on Multisensor Fusion and Integration)
- Category
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Sang-Hoon KIM, Hyoung-Gon KIM, "Facial Region Detection Using Range Color Information" in IEICE TRANSACTIONS on Information,
vol. E81-D, no. 9, pp. 968-975, September 1998, doi: .
Abstract: This paper proposes an object oriented face region detection and tracking method using range color information. Range segmentation of the objects are obtained from the complicated background using disparity histogram (DH). The facial regions among the range segmented objects are detected using skin-color transform technique that provides a facial region enhanced gray-level image. Computationally efficient matching pixel count (MPC) disparity measure is introduced to enhance the matching accuracy by removing the effect of the unexpected noise in the boundary region. Redundancy operations inherent in the area-based matching operation are removed to enhance the processing speed. For the skin-color transformation, the generalized facial color distribution (GFCD) is modeled by 2D Gaussian function in a normalized color space. Disparity difference histogram (DDH) concept from two consecutive frames is introduced to estimate the range information effectively. Detailed geometrical analysis provides exact variation of range information of moving object. The experimental results show that the proposed algorithm works well in various environments, at a rate of 1 frame per second with 512
URL: https://global.ieice.org/en_transactions/information/10.1587/e81-d_9_968/_p
Copy
@ARTICLE{e81-d_9_968,
author={Sang-Hoon KIM, Hyoung-Gon KIM, },
journal={IEICE TRANSACTIONS on Information},
title={Facial Region Detection Using Range Color Information},
year={1998},
volume={E81-D},
number={9},
pages={968-975},
abstract={This paper proposes an object oriented face region detection and tracking method using range color information. Range segmentation of the objects are obtained from the complicated background using disparity histogram (DH). The facial regions among the range segmented objects are detected using skin-color transform technique that provides a facial region enhanced gray-level image. Computationally efficient matching pixel count (MPC) disparity measure is introduced to enhance the matching accuracy by removing the effect of the unexpected noise in the boundary region. Redundancy operations inherent in the area-based matching operation are removed to enhance the processing speed. For the skin-color transformation, the generalized facial color distribution (GFCD) is modeled by 2D Gaussian function in a normalized color space. Disparity difference histogram (DDH) concept from two consecutive frames is introduced to estimate the range information effectively. Detailed geometrical analysis provides exact variation of range information of moving object. The experimental results show that the proposed algorithm works well in various environments, at a rate of 1 frame per second with 512
keywords={},
doi={},
ISSN={},
month={September},}
Copy
TY - JOUR
TI - Facial Region Detection Using Range Color Information
T2 - IEICE TRANSACTIONS on Information
SP - 968
EP - 975
AU - Sang-Hoon KIM
AU - Hyoung-Gon KIM
PY - 1998
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E81-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 1998
AB - This paper proposes an object oriented face region detection and tracking method using range color information. Range segmentation of the objects are obtained from the complicated background using disparity histogram (DH). The facial regions among the range segmented objects are detected using skin-color transform technique that provides a facial region enhanced gray-level image. Computationally efficient matching pixel count (MPC) disparity measure is introduced to enhance the matching accuracy by removing the effect of the unexpected noise in the boundary region. Redundancy operations inherent in the area-based matching operation are removed to enhance the processing speed. For the skin-color transformation, the generalized facial color distribution (GFCD) is modeled by 2D Gaussian function in a normalized color space. Disparity difference histogram (DDH) concept from two consecutive frames is introduced to estimate the range information effectively. Detailed geometrical analysis provides exact variation of range information of moving object. The experimental results show that the proposed algorithm works well in various environments, at a rate of 1 frame per second with 512
ER -
English
