A Tilt-Angle Face Dataset And Its Validation

Since the surveillance cameras are usually mounted at a high position to overlook targets, tilt-angle faces on overhead view are common in the public video surveillance environment. Face recognition approaches based on deep learning models have achieved excellent performance, but there remains a large gap for the overlooking surveillance scenarios. The results of face recognition depend not only on the structure of the model, but also on the completeness and diversity of the training samples. The existing multi-pose face datasets do not cover complete top-view face samples, and the models trained by them thus cannot provide satisfactory accuracy. To this end, this paper pioneers a multi-view tilt-angle face dataset (TFD), which is collected with an elaborately devised overhead capture equipment. TFD contains 11,124 face images from 927 subjects, covering a variety of tilt angles on the overhead view. To verify the validity of the constructed dataset, we further conduct comprehensive face detection and recognition experiments using the corresponding models trained by WiderFace, Webface and our TFD, respectively. Experimental results show that our TFD substantially promotes the face detection and recognition accuracy under the top-view situation. TFD is available at https://github.com/huang1204510135/D FD.

1. Introduction

Human face is one of the most important biometric features in object identification. The currently advanced face recognition technology has achieved state-of-the-art results [1] on public datasets. However, face recognition for pedestrians in public video surveillance encounters a more complex environment. Challenging scenarios such as overhead imaging result in great difficulties to trusted face recognition. In particular, because most of the surveillance cameras are often mounted at a height of about 3.5 meters, when the pedestrian approaches the monitoring camera, only the forehead at a top view can be seen. Due to the lack of holistic facial information, the face recognition for the top-view pose is particularly difficult.