. Face recognition is a non-invasive biometric technology, so it is of interest both to owners of small surveillance systems and for national security purposes.
State-of-the-art face recognition techniques have achieved impressive results with medium- and high-quality face images, but poor performance with low-quality images.
The purpose of the study is to develop and experimentally verify the information technology of face identification based on the image of a face obtained from a video stream, based on an algorithm that provides high identification results on images of low quality and resolution that contain occlusion.
This paper describes research of information technology of person identification by face image, which is based on an algorithm that includes anisotropic diffusion method for image preprocessing, Gabor wavelet transform for image processing, histogram of oriented gradients (HOG) and local binary patterns in 1- dimensional space (1DLBP) for extracting an image feature vector.
Since the spread of the coronavirus disease has created the problem of facial recognition in the presence of a medical mask, which is used as a preventive measure, research on facial recognition and identification technologies has become crucial for all areas of cybersecurity based on digital identity verification.
Experiments with the proposed technology after applying it to occluded images from the SCface database gave a result of 85%, which increased by 2.5% after converting the image format and resolution.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.