Abstract: The key problem of face detecting based on feature.is extracting features.In this paper,a method of feature model based face detecting is proposed.It extracts features from eyes and nose,and then constructs a triangular feature mold component with eyes and nose.The search is taken in the candidate feature image by changing the size of blocks step by step.This processing can obtain separate points of feature mold.And finally proposes a strategy based on the knowledge about facial structure/distribution to search the feature mold.Experimental results prove that this method can rapidly and accurately detect face in an image with complex background.Furthermore,it can perform well for multiple faces.

Key words: feature extract, feature model, face detection

摘要： 特征提取是基于特征的人脸检测的关键。提出了一种利用眼睛和鼻子的灰度特征和几何特征的人脸检测方法。选取眼睛和鼻子作为特征点，构造一个三角的特征模型。另外，此方法对候选特征图像采用逐步改变分块大小的方法进行搜索，得到独立的特征点，并利用人脸结构特点的先验知识建立模型的搜索策略。实验证明，此方法能迅速准确的从复杂背景中检测出人脸，而且对多人脸同样有效。

关键词: 特征提取, 特征模型, 人脸检测