Information technology for person identification by face image in conditions of occlusion
DOI:
https://doi.org/10.31548/energiya1(65).2023.136Abstract
. 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.
Key words: information technology, biometric identification, face recognition
References
World Health Organization (2020). Mask use in the context of COVID-19: interim guidance. World Health Organization, 22.
M. Ngan, P. Grother and K. Hanaoka (2020). Ongoing Face Recognition Vendor Test (FRVT) Part 6A: Face recognition accuracy with masks using pre- COVID-19 algorithms. NIST Interagency/Internal Report (NISTIR), National Institute of Standards and Technology, Gaithersburg, MD. doi: 10.6028/NIST.IR.8311.
K. Hill (2022). Facial Recognition Goes to War. The New York Times. April 7, 2022. Available at: https://www.nytimes.com/2022/04/07/technology/facial-recognition-ukraine-clearview.html
J. Bhuiyan and agencies (2022). Ukraine uses facial recognition software to identify Russian soldiers killed in combat. The Guardian. March 24, 2022. Available at: https://www.theguardian.com/technology/2022/mar/24/ukraine-facial-recognition -identify-russian-soldiers
P. Perona and J. Malik. (1990). Scale-Space and Edge Detection Using Anisotropic Diffusion. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, No. 7, p. 629-639.
O. Bychkov, O. Ivanchenko, K. Merkulova and Y. Zhabska. (2020). Mathematical Methods for Information Technology of Biometric Identification in Conditions of Incomplete Data. Proceedings of the 7th International Conference “Information Technology and Interactions” (IT&I-2020), Kyiv, Ukraine, p. 336-349.
B. Attallah, A. Serir, Y. Chahir, A. Boudjelal. (2017). Histogram of gradient and binarized statistical image features of wavelet subband-based palmprint features extraction. J. Electron. Imag, 26(6) 063006, November 8, 2017. doi: 10.1117/1.JEI.26.6.063006.
Downloads
Published
Issue
Section
License
Relationship between right holders and users shall be governed by the terms of the license Creative Commons Attribution – non-commercial – Distribution On Same Conditions 4.0 international (CC BY-NC-SA 4.0):https://creativecommons.org/licenses/by-nc-sa/4.0/deed.uk
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
