Open-set Face Identification Algorithms with Automatic Detection of Rare Data in the Input Video

Student: Sokolova Anastasiia

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

Educational Programme: Data Mining (Master)

Year of Graduation: 2020

Investigated the problem of detecting "out-of-distribution" images in order to improve the accuracy of face classification algorithms. Special dataset that contains various image anomalies is described. Anomalies detector was trained using this dataset. Implemented 1-NN classification that takes into account information about the distribution of the image. Also, the problem of increasing the computational efficiency of face recognition was investigated. Therefore, used hierarchical algorithm for processing image descriptors. The experimental results of a comparative analysis of the proposed approach with the well-known classification methods for feature vectors extracted using various convolution networks are presented.

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