Aggregate channel features for multi-view face detection

TL;DR

This paper introduces aggregate channel features for multi-view face detection, enhancing feature representation to handle large appearance variances efficiently, resulting in a fast and accurate detector.

Contribution

It proposes a novel aggregate channel feature variant and a multi-view detection approach with score re-ranking, improving face detection performance in the wild.

Findings

Achieves competitive accuracy on AFW and FDDB datasets.

Runs at 42 FPS on VGA images.

Outperforms many existing algorithms in speed and accuracy.

Abstract

Face detection has drawn much attention in recent decades since the seminal work by Viola and Jones. While many subsequences have improved the work with more powerful learning algorithms, the feature representation used for face detection still can't meet the demand for effectively and efficiently handling faces with large appearance variance in the wild. To solve this bottleneck, we borrow the concept of channel features to the face detection domain, which extends the image channel to diverse types like gradient magnitude and oriented gradient histograms and therefore encodes rich information in a simple form. We adopt a novel variant called aggregate channel features, make a full exploration of feature design, and discover a multi-scale version of features with better performance. To deal with poses of faces in the wild, we propose a multi-view detection approach featuring score re-ranking and detection adjustment. Following the learning pipelines in Viola-Jones framework, the multi-view face detector using aggregate channel features shows competitive performance against state-of-the-art algorithms on AFW and FDDB testsets, while runs at 42 FPS on VGA images.