A Fast and Accurate Unconstrained Face Detector

TL;DR

This paper introduces a novel face detection method that uses a new scale-invariant feature and a deep quadratic tree to efficiently detect faces with pose variations and occlusions, achieving state-of-the-art results.

Contribution

It presents the Normalized Pixel Difference feature and a deep quadratic tree for fast, accurate unconstrained face detection in cluttered scenes.

Findings

Achieves state-of-the-art performance on FDDB, GENKI, and CMU-MIT datasets.

Provides a fast detection method suitable for real-time applications.

Demonstrates robustness to pose variations and occlusions.

Abstract

We propose a method to address challenges in unconstrained face detection, such as arbitrary pose variations and occlusions. First, a new image feature called Normalized Pixel Difference (NPD) is proposed. NPD feature is computed as the difference to sum ratio between two pixel values, inspired by the Weber Fraction in experimental psychology. The new feature is scale invariant, bounded, and is able to reconstruct the original image. Second, we propose a deep quadratic tree to learn the optimal subset of NPD features and their combinations, so that complex face manifolds can be partitioned by the learned rules. This way, only a single soft-cascade classifier is needed to handle unconstrained face detection. Furthermore, we show that the NPD features can be efficiently obtained from a look up table, and the detection template can be easily scaled, making the proposed face detector very fast. Experimental results on three public face datasets (FDDB, GENKI, and CMU-MIT) show that the proposed method achieves state-of-the-art performance in detecting unconstrained faces with arbitrary pose variations and occlusions in cluttered scenes.