提出一种新的非线性变换的彩色空间 ″″, 利用次高斯概率分布函数拟合皮肤色度信息, 得到候选区

YC C

r b

域。为了排除候选区域中的非人脸, 首先根据均值和方差信息分割出候选区域中的纹理特征信息, 再通过多尺度

)

(

信息定位眼睛, 然后根据人脸特征的几

形态边缘检测算子检测候选区域的边缘, 利用 边缘方向

PCA PCAED

( )

何形状信息定位其他特征 鼻、嘴 , 通过这些几何特征信息对肤色分割得到的候选区域进行验证, 最终得到正确

的人脸区域。利用3 个实验数据集测试该算法, 并与其它相应的算法相比较, 提出的非线性彩色空间对于肤色分

割具有很好的效果, 且对光照和姿态具有良好的不变性。另外, 利用 信息和几何特征信息检测人脸特征

PCAED

具有很高的定位精度, 定位检测率优于其他方法。实验结果表明, 该算法具有定位准确率高, 漏检率和误检率低

等特点。-

A novel approach for skin segmentation and facial feature extraction is proposed

The proposed skin segmentation is a method for integrating the chrominance components of

″″ . ″″

r b r b

nonlinear YC C color model The chrominance components of nonlinear YC C color space

,

are modeled using a subgaussian probability density function and then the face skin is seg

. ,

mented based on this function In order to authenticate the face candidate regions firstly tex

ture information in face candidate regions is segmented using mean and variance of luminance

, . ,

information and then the eye is located by the PCA edge direction information Finally the

, ,

others features such as nose and mouth also are detected using the geometrical shape infor

. 2 ,

mation As all the above mentioned techniques are simple and efficient the skin segmentation

.

based on nonlinear color spacemethod has the invariability of lighting and pose In the experi

, .

ments themethod has been successfull相关搜索： 纹理特征
人脸
定位
皮肤
纹理
检测
Pca
Facial
Features
Segmentation
人脸
PCA
shape
Feature
based
Approach
pose
face
肤色
人脸