Face recognition is widely used in people's daily life. The face recognition mentioned in this paper is not for the recognition of individual faces, but refers to localization of faces in pictures or videos and counting of faces. The development of face detection algorithms can be divided into three phases, namely the early algorithms, the Adaptive Boosting framework [1], and the deep learning era. Early face recognition used a modular matching technique, which involves using a template image of a face to match various locations in the detection image to determine if there is a face at that location. A representative work was the algorithm proposed by Rowley (Neural network-based face detection[2]), which used a 20x20 dataset to train a Multi-layer Perceptron [3] model with good accuracy, but ran slowly. In 1997, Margineantu et al. proposed a face recognition algorithm in the AdaBoost framework. The boost algorithm is an ensemble learning algorithm based on PAC (probably approximately correct) learning theory. In 2001, Viola and Jones designed a face detection algorithm [4] It used simple Haar-like [5] features and cascaded AdaBoost classifiers to construct a detector that improved detection speed by two orders of magnitude over previous methods and maintained good accuracy. This approach is known as the VJ framework.

Contemporary face detection algorithms have to deal with many challenges such as variations in pose, illumination, and scale. A subclass of the face detection problem that has recently gained increasing attention is occluded face detection, or more specifically, the detection of masked faces. Three years on since the advent of the COVID-19 pandemic, there is still a complete lack of evidence regarding how well existing face detection algorithms perform on masked faces. This article first offers a brief review of state-of-the-art face detectors and detectors made for the masked face problem, along with a review of the existing masked face datasets. We evaluate and compare the performances of a well-representative set of face detectors at masked face detection and conclude with a discussion on the possible contributing factors to their performance.

Deepface is a lightweight face recognition and facial attribute analysis (age, gender, emotion and race) framework for python. It is a hybrid face recognition framework wrapping state-of-the-art models: VGG-Face, Google FaceNet, OpenFace, Facebook DeepFace, DeepID, ArcFace and Dlib. Experiments show that human beings have 97.53% accuracy on facial recognition tasks whereas those models already reached and passed that accuracy level. The easiest way to install deepface is to download it from PyPI. It's going to install the library itself and its prerequisites as well.

Estimating the mask-wearing ratio in public places is important as it enables health authorities to promptly analyze and implement policies. Methods for estimating the mask-wearing ratio on the basis of image analysis have been reported. However, there is still a lack of comprehensive research on both methodologies and datasets. Most recent reports straightforwardly propose estimating the ratio by applying conventional object detection and classification methods. It is feasible to use regression-based approaches to estimate the number of people wearing masks, especially for congested scenes with tiny and occluded faces, but this has not been well studied. A large-scale and well-annotated dataset is still in demand. In this paper, we present two methods for ratio estimation that leverage either a detection-based or regression-based approach. For the detection-based approach, we improved the state-of-the-art face detector, RetinaFace, used to estimate the ratio. For the regression-based approach, we fine-tuned the baseline network, CSRNet, used to estimate the density maps for masked and unmasked faces. We also present the first large-scale dataset, the ``NFM dataset,'' which contains 581,108 face annotations extracted from 18,088 video frames in 17 street-view videos. Experiments demonstrated that the RetinaFace-based method has higher accuracy under various situations and that the CSRNet-based method has a shorter operation time thanks to its compactness.

This work presented a new drone-based face detection dataset Drone LAMS in order to solve issues of low performance of drone-based face detection in scenarios such as large angles which was a predominant working condition when a drone flies high. The proposed dataset captured images from 261 videos with over 43k annotations and 4.0k images with pitch or yaw angle in the range of -90{\deg} to 90{\deg}. Drone LAMS showed significant improvement over currently available drone-based face detection datasets in terms of detection performance, especially with large pitch and yaw angle. Detailed analysis of how key factors, such as duplication rate, annotation method, etc., impact dataset performance was also provided to facilitate further usage of a drone on face detection.