Description

Face detection from low-light images is challenging due to limited photons and inevitable noise, which, to make the task even harder, are often spatially unevenly distributed. A natural solution is to borrow the idea from multi-exposure, which captures multiple shots to obtain well-exposed images under challenging conditions. We propose a low-light face detection method. First, we design an improved ZeroDCE-Net method to increase the image quality under the condition of ensuring that the colors of the image are not distorted. It shows better enhancement effect than other methods in the DARK FACE dataset, especially the low-resolution face details are well preserved. There are a number of small, blurred and partially occluded faces. High-quality implementation /approximation of multi-exposure from a single image is however nontrivial. A low-light illumination is always a problem for some face detection models. However, we can solve this problem by applying a low-light image enhancement on the face detection model. The evaluation results are applied on DCE-NET model as face detection and tested using Dark Face dataset and enhance the image from low light. After enhancement we are going to detect the face by using DNN algorithm.