Image Retrieval with Artificial Neural Networks

Student: Danilov Pavel

Educational Programme: Applied Mathematics and Information Science (Bachelor)

Year of Graduation: 2016

In this work we consider a task of content-based image retrieval. We review a technique for feature extraction from images with artificial neural networks in application for image search. We also consider a few methods for feature extraction: from the whole image only and from its fragment too. We try to achieve search quality and computation efficiency and we touch on techniques for feature modifications to that end. In addition we consider two approaches for search quality estimation and show superiority of the first approach over another one. Finally, we estimate search quality of descriptors on neural networks with selected metrics and compare it with another classical descriptors in computer vision field.

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