A hybrid technique for facial feature point detection
A hybrid technique for facial feature point detection
复制标题
DOI：
10.1109/iai.2002.999905
复制
发表时间：
2002-04
期刊：
影响因子：
--
通讯作者：
M. Gargesha;S. Panchanathan
中科院分区：
文献类型：
--
作者：
M. Gargesha;S. Panchanathan
从彩色图像中检测人脸特征点的现有技术包括模板匹配、人脸几何和对称性分析、数学形态学、亮度和色度分析以及PCA。然而，这些技术在存在尺度变化的情况下受到性能差的困扰。在本文中，提出了一种混合技术，采用了上述方法的组合沿着与曲率分析的强度表面的人脸图像，以提供一个上级性能降低计算复杂性，即使在规模变化的存在。
Existing techniques for facial feature point detection from color images include template matching, facial geometry and symmetry analysis, mathematical morphology, luminance and chrominance analysis, and PCA. However, these techniques are plagued by poor performance in the presence of scale variations. In this paper, a hybrid technique is proposed that employs a combination of the above approaches along with curvature analysis of the intensity surface of the face image in order to provide a superior performance with reduced computational complexity, even in the presence of scale variations.