基于示例学习的图像人脸检测技术

Example-based Learning for Human Face Detection

描述了一种基于示例学习的方法来检测具有复杂背景的图像中正面人脸的位置。这项技术使用了图像模型聚类的方式构造了人脸模式的分布。针对每一个图像 ,计算图像局部分布与基于分布的模板之间的特征矢量差异。然后基于这个差异 。

This paper presents an example based learning approach for locating human faces in complex scenes.The technique models the distribution of human face patterns by means of a few view based ″face″model clusters.At each image location,a difference feature vectors is computed between the local image pattern and the distribution based model.Based on the difference feature feature vector measurements,a trained classifier determines whether or not a human face exists at the current image location.