From Facial Parts Responses to Face Detection: A Deep Learning Approach

TL;DR

This paper introduces a deep learning face detection method that scores facial parts responses considering spatial structure, enabling high accuracy detection even with occlusions and pose variations, while maintaining practical speed.

Contribution

A novel deep convolutional network that scores facial parts responses based on spatial structure, improving detection under occlusion and pose variation.

Findings

Achieves 90.99% recall on FDDB benchmark.

Outperforms state-of-the-art by 2.91%.

Detects faces with partial visibility and varied poses.

Abstract

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.