From Facial Parts Responses to Face Detection: A Deep Learning Approach
This addresses the bottleneck of detecting faces under severe occlusion and unconstrained poses, which is a key challenge in computer vision applications.
The paper tackles face detection by scoring facial parts responses based on spatial structure to handle occlusion and pose variation, achieving a 90.99% recall rate on FDDB, which is 2.91% higher than the state-of-the-art.
In this paper, we propose a novel deep convolutional network (DCN) that achieves outstanding performance on FDDB, PASCAL Face, and AFW. Specifically, our method achieves a high recall rate of 90.99% on the challenging FDDB benchmark, outperforming the state-of-the-art method by a large margin of 2.91%. Importantly, we consider finding faces from a new perspective through scoring facial parts responses by their spatial structure and arrangement. The scoring mechanism is carefully formulated considering challenging cases where faces are only partially visible. This consideration allows our network to detect faces under severe occlusion and unconstrained pose variation, which are the main difficulty and bottleneck of most existing face detection approaches. We show that despite the use of DCN, our network can achieve practical runtime speed.