EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Autonomous Face Classification Online Self-Training System Using Pretrained ResNet50 and Multinomial Naïve Bayes

Łukasz Maciura iD, Tomasz Cieplak iD, Damian Pliszczuk iD, Michał Maj iD, Tomasz Rymarczyk iD

Sensors · 14.06.2023 · 23 (12) · 5554

DOI: 10.3390/s23125554 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 14.06.2023. Verfasst von Łukasz Maciura und 4 weiteren Autor:innen. Beteiligte Einrichtung: Research and Development Center, Netrix S.A., 20-704 Lublin, Poland. Hauptthemen laut MEDLINE: Neural Networks, Computer, Algorithms. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents a novel, autonomous learning system working in real-time for face recognition. Multiple convolutional neural networks for face recognition tasks are available; however, these networks need training data and a relatively long training process as the training speed depends on hardware characteristics. Pretrained convolutional neural networks could be useful for encoding face images (after classifier layers are removed). This system uses a pretrained ResNet50 model to encode face images from a camera and the Multinomial Naïve Bayes for autonomous training in the real-time classification of persons. Faces of several persons visible in a camera are tracked using special cognitive tracking agents who deal with machine learning models. After a face in a new position of the frame appears (in a place where there was no face in the previous frames), the system checks if it is novel or not using a novelty detection algorithm based on an SVM classifier; if it is unknown, the system automatically starts training. As a result of the conducted experiments, one can conclude that good conditions provide assurance that the system can learn the faces of a new person who appears in the frame correctly. Based on our research, we can conclude that the critical element of this system working is the novelty detection algorithm. If false novelty detection works, the system can assign two or more different identities or classify a new person into one of the existing groups.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerAlgorithmsHumansBayes TheoremMachine Learning

Stichwörter der Autor:innen

Multinomial Naïve Bayes classifierautonomous systemsconvolutional neural networksface recognitiononline learning

Autor:innen und Institutionen

  • Research and Development Center, Netrix S.A., 20-704 Lublin, Poland.
  • Department of Organization of Enterprise, Faculty of Management, Lublin University of Technology, 20-618 Lublin, Poland.
  • Faculty of Computer Science, WSEI University, 20-209 Lublin, Poland.

ORCID-Profile: Łukasz Maciura, Tomasz Cieplak, Damian Pliszczuk, Michał Maj, Tomasz Rymarczyk

Zitieren

APA

Maciura, Ł., Cieplak, T., Pliszczuk, D., Maj, M., & Rymarczyk, T. (2023). Autonomous Face Classification Online Self-Training System Using Pretrained ResNet50 and Multinomial Naïve Bayes. Sensors, 23(12), 5554. https://doi.org/10.3390/s23125554

Vancouver

Maciura Ł, Cieplak T, Pliszczuk D, Maj M, Rymarczyk T. Autonomous Face Classification Online Self-Training System Using Pretrained ResNet50 and Multinomial Naïve Bayes. Sensors. 2023;23(12):5554. doi:10.3390/s23125554

BibTeX
@article{Maciura2023,
  author = {Maciura, Łukasz and Cieplak, Tomasz and Pliszczuk, Damian and Maj, Michał and Rymarczyk, Tomasz},
  title = {Autonomous Face Classification Online Self-Training System Using Pretrained ResNet50 and Multinomial Naïve Bayes},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {12},
  pages = {5554},
  doi = {10.3390/s23125554}
}
Kostenlos starten →