# A Fast and Accurate Unconstrained Face Detector

arXiv: https://arxiv.org/abs/1408.1656 · HTML: https://mlsanity.com/paper/1408.1656/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Aug 2014.

## Built on by (most cited first, 5 of 5)

- [Going Deeper Into Face Detection: A Survey](https://mlsanity.com/paper/2103.14983/) (2021)
- [Privacy-preserving Online AutoML for Domain-Specific Face Detection](https://mlsanity.com/paper/2203.08399/) (2022)
- [Seeing Faces in Things: A Model and Dataset for Pareidolia](https://mlsanity.com/paper/2409.16143/) (2024)
- [Real-time AdaBoost cascade face tracker based on likelihood map and optical flow](https://mlsanity.com/paper/2210.13885/) (2022)
- [Wide Aspect Ratio Matching for Robust Face Detection](https://mlsanity.com/paper/2103.05993/) (2021)

## Abstract (arXiv)

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.