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

Facial Features ManipulatIon Using Neural Network

Student: Vladislav Roslovets

Supervisor: Denis Derkach

Faculty: Faculty of Computer Science

Educational Programme: Applied Mathematics and Information Science (Bachelor)

Year of Graduation: 2021

At the moment, photography is one of the most important technologies for storing and transmitting information. According to App Annie statistics for the first quarter of 2021, the social network Instagram at number four in monthly active users, which indicates the importance of photo and video content on the network. Social networks and other applications provide users with the ability to use various filters and masks to change the original photo. People often edit facial attributes or use beautification. Tools and techniques for the digital processing of graphics and images have evolved since the 1960s. At the moment, there are many tools for working with images on both mobile devices and desktop. Due to the significant improvement in graphics cards, the use of neural networks for working with images has become increasingly popular. In 2012, the convolutional network achieved a 16% error on the ImageNet [1] dataset, which showed the promise of these architectures in the field of image processing. The next significant step in the field of image processing was the development of generative adversarial networks [2] that allow the generation of photorealistic images. The GAN [2] approach has become common for image editing. The main goal of this work is the improvement of the idea of changing the attributes of faces using neural networks, as well as the implementation of a program complex for using the results obtained.

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