Reconstruction and enhancement techniques for overcoming occlusion in facial recognition
Abstract 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 m...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-05-01
|
| Series: | EURASIP Journal on Image and Video Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13640-025-00670-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849730978648424448 |
|---|---|
| author | Filip Pleško Tomáš Goldmann Kamil Malinka |
| author_facet | Filip Pleško Tomáš Goldmann Kamil Malinka |
| author_sort | Filip Pleško |
| collection | DOAJ |
| description | Abstract 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. |
| format | Article |
| id | doaj-art-55cd18eceef845979aeadde9689cb569 |
| institution | DOAJ |
| issn | 1687-5281 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Image and Video Processing |
| spelling | doaj-art-55cd18eceef845979aeadde9689cb5692025-08-20T03:08:43ZengSpringerOpenEURASIP Journal on Image and Video Processing1687-52812025-05-012025112110.1186/s13640-025-00670-7Reconstruction and enhancement techniques for overcoming occlusion in facial recognitionFilip Pleško0Tomáš Goldmann1Kamil Malinka2Faculty of Information Technology, Brno University of TechnologyFaculty of Information Technology, Brno University of TechnologyFaculty of Information Technology, Brno University of TechnologyAbstract 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.https://doi.org/10.1186/s13640-025-00670-7Facial recognitionFacial reconstructionImage enhancementImage inpaintingArcFaceMagFace |
| spellingShingle | Filip Pleško Tomáš Goldmann Kamil Malinka Reconstruction and enhancement techniques for overcoming occlusion in facial recognition EURASIP Journal on Image and Video Processing Facial recognition Facial reconstruction Image enhancement Image inpainting ArcFace MagFace |
| title | Reconstruction and enhancement techniques for overcoming occlusion in facial recognition |
| title_full | Reconstruction and enhancement techniques for overcoming occlusion in facial recognition |
| title_fullStr | Reconstruction and enhancement techniques for overcoming occlusion in facial recognition |
| title_full_unstemmed | Reconstruction and enhancement techniques for overcoming occlusion in facial recognition |
| title_short | Reconstruction and enhancement techniques for overcoming occlusion in facial recognition |
| title_sort | reconstruction and enhancement techniques for overcoming occlusion in facial recognition |
| topic | Facial recognition Facial reconstruction Image enhancement Image inpainting ArcFace MagFace |
| url | https://doi.org/10.1186/s13640-025-00670-7 |
| work_keys_str_mv | AT filipplesko reconstructionandenhancementtechniquesforovercomingocclusioninfacialrecognition AT tomasgoldmann reconstructionandenhancementtechniquesforovercomingocclusioninfacialrecognition AT kamilmalinka reconstructionandenhancementtechniquesforovercomingocclusioninfacialrecognition |