Development on a Video-to-Text Recognition Module

Student: Doroshenko Pavel

Faculty: HSE Tikhonov Moscow Institute of Electronics and Mathematics (MIEM HSE)

Educational Programme: Information Science and Computation Technology (Bachelor)

Year of Graduation: 2019

The purpose of this work is creation of a module for real-time text recognition from a video stream for a Linux system. This paper discusses ways to recognize text from video, contains a comparative analysis of existing technical solutions in this area, analysis and comparison of development tools and approaches to solving the problem, various algorithms for segmentation and filtering text in the image review. As a result of the work, a module was obtained for the Linux system performing the task that was uploaded to the training server, as well as service management tools were created. Keywords: OCR (Optical Character Recognition), segmentation, filtering, binarization. The current research paper contains 13 illustrations, 4 tables, 5 annexes and 8 used sources. The overall volume of the paper is 43 pages.

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