Facial clustering of photos from a social network for mobile platforms

Student: Kuporosova Anastasiya

Faculty: Faculty of Informatics, Mathematics, and Computer Science (HSE Nizhny Novgorod)

Educational Programme: Software Engineering (Bachelor)

Final Grade: 9

Year of Graduation: 2019

The present work is aimed to explore different clustering algorithms and convolutional neural networks that extract face features for finding the best combination. The dataset for experimental runs of algorithms was created using Instagram social network. Instagram was chosen due to there are a lot of photos of different people that allows creating a satisfactory dataset for face clustering. An analytic review of the literature on the methods of face clustering was conducted and algorithms which can show good clustering quality was chosen. As the result the Android mobile application was created which clusters faces and makes a directory per cluster, using the best combination of feature extractor and clustering algorithm after the exploration step.

Full text (added May 20, 2019)

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