ICCV 2015 email to get code and model
http://personal.ie.cuhk.edu.hk/~ys014/projects/Faceness/Faceness.html
本文主要是用CNN进行人脸局部属性检测,然后各个部件综合起来得到人脸检测结果。
本文主要包含三个步骤:
3.1. Partness Maps Extraction 人脸部件提取
网络结构如下:
其中我们提取5个人脸部件
3.2. Ranking Windows by Faceness Measure
This problem can be simply formulated as maximum a posteriori (MAP)
3.3. Face Detection
we refine these windows by joint training face classification and bounding
box regression using a CNN similar to the AlexNet [16].