• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site
National Research University Higher School of EconomicsStudent ThesesDevelopment of the Face Varification System on the Basis of the Convolutional Neural Networks

Student
Title
Supervisor
Faculty
Educational Programme
Final Grade
Year of Graduation
Diana Ibragimova
Development of the Face Varification System on the Basis of the Convolutional Neural Networks
Business Informatics
(Bachelor’s programme)
2016
In the final qualifying work, the convolutional neural networks were considered and a prototype of the face verification system by individual photos was built.

In the theoretical part, the critical analysis of the large body of literature on the subject about neural networks was conducted. Besides, the existing face recognition algorithms and the available methods of the implementation of the system were conducted and the best tool for this task has been chosen.

The general part describes the implementation of the algorithm to the prototype of the face recognition system. In addition, the prototype of this system was developed and the test results of the work of the program are given in this paper.

The part of the experimental studies carried out the comparative characteristics of the system for several models of neural networks and the best parameters of the system have been chosen by fixing the possibility of the second type of errors and at the same time minimizing the likelihood of the first type errors. As a result, the model with the best results was selected.

Graduation project contains applications that contain the data from the test samples, the results of parameters comparison and the program code.

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