• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Face Recognition Service for Person Identification

Student: Konstantinovskiy Nikita

Supervisor: Dmitry Alexandrov

Faculty: Faculty of Computer Science

Educational Programme: Software Engineering (Bachelor)

Year of Graduation: 2018

This document presents the architecture, functionality and technologies used in a service for facial recognition. The service is designed to be integrated as a framework into a mobile application on the iOS platform. The service is designed to reduce the time and cost of using face recognition services, by reducing the load on Internet traffic and conducting most of the process for recognizing faces on a mobile device. The service architecture is used a deep neural network to encode the detected faces. The client- server architecture is required to determine the person. The server stores a database with face codes and a classifier that determines the person. As a result, we demonstrate the service architecture and the opportunities for approaches and models of machine learning to develop a service for face recognition. The paper contains 42 pages, 3 chapters, 8 illustrations, 37 bibliography items, 8 appendices.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses