Reconstruction and enhancement techniques for overcoming occlusion in facial recognition

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F26%3A0193306" target="_blank" >RIV/00216305:26230/26:0193306 - isvavai.cz</a>
Result on the web
<a href="https://jivp-eurasipjournals.springeropen.com/articles/10.1186/s13640-025-00670-7" target="_blank" >https://jivp-eurasipjournals.springeropen.com/articles/10.1186/s13640-025-00670-7</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1186/s13640-025-00670-7" target="_blank" >10.1186/s13640-025-00670-7</a>

Result language
angličtina
Original language name
Reconstruction and enhancement techniques for overcoming occlusion in facial recognition
Original language description
Facial occlusions in surveillance footage can obscure important features, preventing facial recognition systems from identifying people. This work focuses on reconstructing these missing facial parts using Generative Adversarial Networks (GANs) to improve facial recognition accuracy while maintaining a low false acceptance rate. Additionally, we investigate how the generated images can be further enhanced using various image enhancement methods to boost recognition accuracy. To evaluate the results, we conduct experiments with widely used face embedding models, such as QMagFace and ArcFace, to determine whether image reconstruction and enhancement improve face recognition accuracy.
Czech name
—
Czech description
—

Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)