Small Face Detection with Deep Learning Approaches

Abstract

This thesis considers small face detection in uncontrolled environments and develops robust deep learning approaches for this challenging problem. A novel multi-scale face detector is developed by integrating novel anchor design, efficient regression loss and additional detection layers. Several multi-scale dense convolutional networks are developed to boost up the detection of small faces. Experimental results on public face databases demonstrate that the proposed methods outperform the state-of-the-art methods (e.g. YOLOv3) for detection of small faces.