Publication detail

Scalable Person Identification System for Real-time Applications

RAJNOHA, M.

Original Title

Scalable Person Identification System for Real-time Applications

English Title

Scalable Person Identification System for Real-time Applications

Type

conference paper

Language

en

Original Abstract

Face recognition systems can play significant role in our every day lives. This paper proposes a scalable system for person identification based on face recognition methods and its implementation that utilizes queues, containers and microservices architecture. The proposed system uses a GPU acceleration therefore it can run in real-time. It utilizes two deep neural networks - Single Shot Multibox Detector (SSD) for a face detection and Facenet for a face recognition.

English abstract

Face recognition systems can play significant role in our every day lives. This paper proposes a scalable system for person identification based on face recognition methods and its implementation that utilizes queues, containers and microservices architecture. The proposed system uses a GPU acceleration therefore it can run in real-time. It utilizes two deep neural networks - Single Shot Multibox Detector (SSD) for a face detection and Facenet for a face recognition.

Keywords

facerecognition; scalable; realtime; detection; microservices; queues; identification

Released

25.04.2019

Publisher

Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií

Location

Brno

ISBN

978-80-214-5735-5

Book

Proceedings of the 25th Conference STUDENT EEICT 2019

Pages from

500

Pages to

504

Pages count

5

BibTex


@inproceedings{BUT156676,
  author="Martin {Rajnoha}",
  title="Scalable Person Identification System for Real-time Applications",
  annote="Face recognition systems can play significant role in our every day lives. This paper proposes a scalable system for person identification based on face recognition methods and its implementation that utilizes queues, containers and microservices architecture. The proposed system uses a GPU acceleration therefore it can run in real-time. It utilizes two deep neural networks - Single Shot Multibox Detector (SSD) for a face detection and Facenet for a face recognition.",
  address="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií",
  booktitle="Proceedings of the 25th Conference STUDENT EEICT 2019",
  chapter="156676",
  howpublished="online",
  institution="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií",
  year="2019",
  month="april",
  pages="500--504",
  publisher="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií",
  type="conference paper"
}