Методи розпізнавання обличчя у системах відеоспостереження з використанням машинного навчання

Simple item page
dc.citation.epage42
dc.citation.issue2
dc.citation.journalTitleІнфокомунікаційні технології та електронна інженерія
dc.citation.spage33
dc.citation.volume3
dc.contributor.affiliationНаціональний університет “Львівська політехніка”
dc.contributor.affiliationLviv Polytechnic National University
dc.contributor.authorМрак, В.
dc.contributor.authorMrak, V.
dc.coverage.placenameЛьвів
dc.coverage.placenameLviv
dc.date.accessioned2025-07-22T11:15:30Z
dc.date.created2023-02-28
dc.date.issued2023-02-28
dc.description.abstractДосліджено методи розпізнавання облич із визначенням найпридатнішого для системи безпеки на основі розпізнавання облич з камер відеоспостереження. Проаналізовано часові витрати цих методів та їх стійкість до спотворень геометричного масштабу та поворотів у різних площинах. Для експериментів згенеровано власні набори даних. Особливу увагу приділено компромісу між швидкістю та точністю розглянутих методів для їх використання як першого етапу системи безпеки на основі розпізнавання обличчя у відеопотоці. Проведені дослідження показали, що найефективнішими виявилися методи RetinaFace-MobileNet0.25, FaceBoxes, SCRFD500MF, CenterFace; RetinaFaceResNet125, DSFD, RetinaFaceMobileNet0.25 які стійкі до повороту обличчя. Крім того, під час вибору найоптимальнішого методу розпізнавання обличчя для застосування в системі безпеки враховували наявність інформативних параметрів оличчя, а також той факт, що методи розпізнавання, які використовуються на наступному етапі, мають обмеження щодо стійкості до афінних перетвотрень.
dc.description.abstractThe article is dedicated to the investigation of face identification methods and aims to determine the most suitable one for a security system based on facial recognition from surveillance cameras. The time costs of these methods and their robustness against geometric scale distortions and rotations in various planes have been analyzed. Custom datasets have been generated for experimentation purposes. Special attention has been given to striking a balance between the speed and accuracy of the examined methods for their utilization as the initial stage of a security system based on facial recognition in a video stream. The conducted research has revealed that the most effective methods are RetinaFace-MobileNet0.25, FaceBoxes, SCRFD500MF, and CenterFace; RetinaFaceResNet125, DSFD, and RetinaFaceMobile0.25 which are resilient to facial rotations. Furthermore, when selecting the most optimal facial recognition method for application within a security system, the presence of informative facial parameters was taken into account, as well as the fact that the recognition methods used in the subsequent stage have their limitations concerning resilience to affine transformations.
dc.format.extent33-42
dc.format.pages10
dc.identifier.citationМрак В. Методи розпізнавання обличчя у системах відеоспостереження з використанням машинного навчання / В. Мрак // Інфокомунікаційні технології та електронна інженерія. — Львів : Видавництво Львівської політехніки, 2023. — Том 3. — № 2. — С. 33–42.
dc.identifier.citationenMrak V. Face recognition methods in video surveillance systems using machine learning / V. Mrak // Infocommunication Technologies and Electronic Engineering. — Lviv : Lviv Politechnic Publishing House, 2023. — Vol 3. — No 2. — P. 33–42.
dc.identifier.doidoi.org/10.23939/ictee2023.02.033
dc.identifier.urihttps://ena.lpnu.ua/handle/ntb/111455
dc.language.isouk
dc.publisherВидавництво Львівської політехніки
dc.publisherLviv Politechnic Publishing House
dc.relation.ispartofІнфокомунікаційні технології та електронна інженерія, 2 (3), 2023
dc.relation.ispartofInfocommunication Technologies and Electronic Engineering, 2 (3), 2023
dc.relation.references[1] Zhang, K., Zhang, Z., Li, Z., & Qiao, Y. (2016). Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Processing Letters, 23(10), 1499–1503. DOI: 10.1109/lsp.2016.2603342.
dc.relation.references[2] Zhang, S., Zhu, X., Lei, Z., Shi, H., Wang, X., & Li, S. Z. (2017). FaceBoxes: A CPU real-time face detector with high accuracy. 2017 IEEE International Joint Conference on Biometrics (IJCB). DOI: 10.1109/btas.2017.8272675.
dc.relation.references[3] Ren, S., He, K., Girshick, R., & Sun, J. (2017). Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), 1137–1149. https://doi.org/10.1109/tpami.2016.2577031.
dc.relation.references[4] Deng, J., Guo, J., Ververas, E., Kotsia, I., & Zafeiriou, S. (2020). Retinaface: Single-shot multilevel face localisation in the wild. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr42600.2020.00525
dc.relation.references[5] Xu, Y., Yan, W., Yang, G., Luo, J., Li, T., & He, J. (2020). Centerface: Joint face detection and alignment using face as point. Scientific Programming, 2020, 1–8. https://doi.org/10.1155/2020/7845384
dc.relation.references[6] Guo, J., Deng, J., Lattas, A., & Zafeiriou, S. (2021, May 10). Sample and computation redistribution for efficient face detection. arXiv.org. Retrieved July 15, 2023, from https://arxiv.org/abs/2105.04714
dc.relation.references[7] Zhang, E., & Zhang, Y. (2009). Average precision. Encyclopedia of Database Systems, 192–193. https://doi.org/10.1007/978-0-387-39940-9_482
dc.relation.references[8] Deepinsight. (n. d.). Insightface/model_zoo at master • deepinsight/insightface. GitHub. Retrieved July 15, 2023, from https://github.com/deepinsight/insightface/tree/master/model_zoo
dc.relation.references[9] Yang, S., Luo, P., Loy, C. C., & Tang, X. (2016). Wider face: A face detection benchmark. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr.2016.596
dc.relation.references[10] Timesler (n. d.). Timesler/facenet-pytorch: Pretrained Pytorch Face Detection (MTCNN) and facial recognition (InceptionResnet) models. GitHub. Retrieved July 15, 2023, from https://github.com/timesler/facenet-pytorch
dc.relation.references[11] Zisianw (n. d.). Zisianw/faceboxes.pytorch: A pytorch implementation of faceboxes. GitHub. Retrieved July 15, 2023, from https://github.com/zisianw/FaceBoxes.PyTorch
dc.relation.references[12] Hukkelas (n. d.). Hukkelas/DSFD-pytorch-inference: A high-performance pytorch implementation of face detection models, including RetinaFace and DSFD. GitHub. Retrieved July 15, 2023, from https://github.com/hukkelas/DSFD-Pytorch-Inference
dc.relation.references[13] Star-Clouds (n. d.). Star-Clouds/Centerface: Face detection. GitHub. Retrieved July 15, 2023, from https://github.com/Star-Clouds/CenterFace
dc.relation.references[14] Deepinsight (n. d.). Insightface/python-package at master • deepinsight/insightface. GitHub. Retrieved July 15, 2023, from https://github.com/deepinsight/insightface/tree/master/pythonpackage
dc.relation.references[15] Unique, worry-free model photos. Generated Photos (n. d.). Retrieved July 15, 2023, from https://generated.photos/
dc.relation.references[16] Character Creator (CC) is a full character creation solution for designers to easily generate, import and customize stylized or realistic character. Retrieved July 10, 2023, from https://www.reallusion.com/character-creator/
dc.relation.references[17] Olena Yakovleva, Andrii Kovtunenko, Valentyn Liubchenko, Vadym Honcharenkoand Oleg Kobylin. Face Detection for Video Surveillance-based Security System COLINS-2023: 7th International Conference on Computational Linguistics and Intelligent Systems, April 20–21, 2023, Kharkiv, Ukraine, 69–86.
dc.relation.referencesen[1] Zhang, K., Zhang, Z., Li, Z., & Qiao, Y. (2016). Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Processing Letters, 23(10), 1499–1503. DOI: 10.1109/lsp.2016.2603342.
dc.relation.referencesen[2] Zhang, S., Zhu, X., Lei, Z., Shi, H., Wang, X., & Li, S. Z. (2017). FaceBoxes: A CPU real-time face detector with high accuracy. 2017 IEEE International Joint Conference on Biometrics (IJCB). DOI: 10.1109/btas.2017.8272675.
dc.relation.referencesen[3] Ren, S., He, K., Girshick, R., & Sun, J. (2017). Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), 1137–1149. https://doi.org/10.1109/tpami.2016.2577031.
dc.relation.referencesen[4] Deng, J., Guo, J., Ververas, E., Kotsia, I., & Zafeiriou, S. (2020). Retinaface: Single-shot multilevel face localisation in the wild. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr42600.2020.00525
dc.relation.referencesen[5] Xu, Y., Yan, W., Yang, G., Luo, J., Li, T., & He, J. (2020). Centerface: Joint face detection and alignment using face as point. Scientific Programming, 2020, 1–8. https://doi.org/10.1155/2020/7845384
dc.relation.referencesen[6] Guo, J., Deng, J., Lattas, A., & Zafeiriou, S. (2021, May 10). Sample and computation redistribution for efficient face detection. arXiv.org. Retrieved July 15, 2023, from https://arxiv.org/abs/2105.04714
dc.relation.referencesen[7] Zhang, E., & Zhang, Y. (2009). Average precision. Encyclopedia of Database Systems, 192–193. https://doi.org/10.1007/978-0-387-39940-9_482
dc.relation.referencesen[8] Deepinsight. (n. d.). Insightface/model_zoo at master • deepinsight/insightface. GitHub. Retrieved July 15, 2023, from https://github.com/deepinsight/insightface/tree/master/model_zoo
dc.relation.referencesen[9] Yang, S., Luo, P., Loy, C. C., & Tang, X. (2016). Wider face: A face detection benchmark. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr.2016.596
dc.relation.referencesen[10] Timesler (n. d.). Timesler/facenet-pytorch: Pretrained Pytorch Face Detection (MTCNN) and facial recognition (InceptionResnet) models. GitHub. Retrieved July 15, 2023, from https://github.com/timesler/facenet-pytorch
dc.relation.referencesen[11] Zisianw (n. d.). Zisianw/faceboxes.pytorch: A pytorch implementation of faceboxes. GitHub. Retrieved July 15, 2023, from https://github.com/zisianw/FaceBoxes.PyTorch
dc.relation.referencesen[12] Hukkelas (n. d.). Hukkelas/DSFD-pytorch-inference: A high-performance pytorch implementation of face detection models, including RetinaFace and DSFD. GitHub. Retrieved July 15, 2023, from https://github.com/hukkelas/DSFD-Pytorch-Inference
dc.relation.referencesen[13] Star-Clouds (n. d.). Star-Clouds/Centerface: Face detection. GitHub. Retrieved July 15, 2023, from https://github.com/Star-Clouds/CenterFace
dc.relation.referencesen[14] Deepinsight (n. d.). Insightface/python-package at master • deepinsight/insightface. GitHub. Retrieved July 15, 2023, from https://github.com/deepinsight/insightface/tree/master/pythonpackage
dc.relation.referencesen[15] Unique, worry-free model photos. Generated Photos (n. d.). Retrieved July 15, 2023, from https://generated.photos/
dc.relation.referencesen[16] Character Creator (CC) is a full character creation solution for designers to easily generate, import and customize stylized or realistic character. Retrieved July 10, 2023, from https://www.reallusion.com/character-creator/
dc.relation.referencesen[17] Olena Yakovleva, Andrii Kovtunenko, Valentyn Liubchenko, Vadym Honcharenkoand Oleg Kobylin. Face Detection for Video Surveillance-based Security System COLINS-2023: 7th International Conference on Computational Linguistics and Intelligent Systems, April 20–21, 2023, Kharkiv, Ukraine, 69–86.
dc.relation.urihttps://doi.org/10.1109/tpami.2016.2577031
dc.relation.urihttps://doi.org/10.1109/cvpr42600.2020.00525
dc.relation.urihttps://doi.org/10.1155/2020/7845384
dc.relation.urihttps://arxiv.org/abs/2105.04714
dc.relation.urihttps://doi.org/10.1007/978-0-387-39940-9_482
dc.relation.urihttps://github.com/deepinsight/insightface/tree/master/model_zoo
dc.relation.urihttps://doi.org/10.1109/cvpr.2016.596
dc.relation.urihttps://github.com/timesler/facenet-pytorch
dc.relation.urihttps://github.com/zisianw/FaceBoxes.PyTorch
dc.relation.urihttps://github.com/hukkelas/DSFD-Pytorch-Inference
dc.relation.urihttps://github.com/Star-Clouds/CenterFace
dc.relation.urihttps://github.com/deepinsight/insightface/tree/master/pythonpackage
dc.relation.urihttps://generated.photos/
dc.relation.urihttps://www.reallusion.com/character-creator/
dc.rights.holder© Національний університет “Львівська політехніка”, 2023
dc.subjectрозпізнавання обличчя
dc.subjectMTCNN
dc.subjectвбудовування
dc.subjectFaceBoxes
dc.subjectDSFD
dc.subjectRetinaFace
dc.subjectCenterFace
dc.subjectSCRFD
dc.subjectсистема безпеки
dc.subjectвідеоспостереження
dc.subjectface detection
dc.subjectembeddings
dc.subjectMTCNN
dc.subjectFaceBoxes
dc.subjectDSFD
dc.subjectRetinaFace
dc.subjectCenterFace
dc.subjectSCRFD
dc.subjectsecurity system
dc.subjectvideo surveillance
dc.subject.udc621.126
dc.titleМетоди розпізнавання обличчя у системах відеоспостереження з використанням машинного навчання
dc.title.alternativeFace recognition methods in video surveillance systems using machine learning
dc.typeArticle

Files

Original bundle

Now showing 1 - 2 of 2
Thumbnail Image
Name:
2023v3n2_Mrak_V-Face_recognition_methods_in_33-42.pdf
Size:
1.14 MB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
2023v3n2_Mrak_V-Face_recognition_methods_in_33-42__COVER.png
Size:
948.6 KB
Format:
Portable Network Graphics
Download

License bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.75 KB
Format:
Plain Text
Description:
Download

Collections

Infocommunication Technologies and Electronic Engineering. – 2023. – Vol. 3, No. 2