Minimal support based multi-view face detection: Issues and Implementation

摘要

Multi-view face detection is a challenging problem due to dramatic appearance changes under various pose, illumination and expression conditions. In this paper we consider the problem of multi-view face detection. In this paper detection, It propose to apply Deep Convolutional Neural Networks (DCNN) as the post filter, which is known to be able to extract effective features automatically during learning. The proposed method has minimal complexity, unlike other recent deep learning object detection methods, it does not require additional components such as segmentation, bounding box regression, or SVM classifiers. We build a deep convolutional neural network that can simultaneously learn the faceonface decision, the face pose estimation problem, and the facial landmark localization problem. We show that such a multi-task learning scheme can further improve the classifier's accuracy. Evaluations on popular face detection benchmark data sets show that our single model face detector algorithm has similar or better performance compared other previous methods, which are more complex and require annotations of either different poses or facial landmarks.