Survey of Face Detection on Low-quality Images
This highlights a critical gap for practical applications such as surveillance systems, but it is incremental as it builds on existing face detection research.
The paper reviewed state-of-the-art face detectors and found they perform poorly on low-quality images, with significant degradation in accuracy when tested under conditions like blur and noise.
Face detection is a well-explored problem. Many challenges on face detectors like extreme pose, illumination, low resolution and small scales are studied in the previous work. However, previous proposed models are mostly trained and tested on good-quality images which are not always the case for practical applications like surveillance systems. In this paper, we first review the current state-of-the-art face detectors and their performance on benchmark dataset FDDB, and compare the design protocols of the algorithms. Secondly, we investigate their performance degradation while testing on low-quality images with different levels of blur, noise, and contrast. Our results demonstrate that both hand-crafted and deep-learning based face detectors are not robust enough for low-quality images. It inspires researchers to produce more robust design for face detection in the wild.