magistrsko delo
Timi Lah (Author), Damjan Vlaj (Mentor), Mirjam Sepesy Maučec (Co-mentor)

Abstract

V magistrskem delu bomo predstavili tehnologije digitalne televizije preko različnih medijev (prizemna televizija, satelitska televizija, IPTV ...). Razčlenili bomo transportni tok digitalne televizije in podali različne formate podnapisov, ki se danes uporabljajo v praksi. V nadaljevanju se bomo poglobili v delovanje optične prepoznave znakov na nivoju knjižnice Tesseract OCR in spoznali različne postopke identifikacije jezika besedila. V sklepnem delu magistrske naloge bomo sestavili programsko opremo, ki bo iz toka digitalne televizije izločila vse sledi podnapisov in prepoznala jezik posamezne sledi.

Keywords

digitalna televizija;optična prepoznava znakov;podnapisi;identifikacija jezika;magistrske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher: T. Lah
UDC: 621.397.743:778.535(043.2)
COBISS: 21237526 Link will open in a new window
Views: 930
Downloads: 94
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Error detection in the subtitle transport stream of the digital television
Secondary abstract: In this master's thesis, we will get acquainted with technologies for digital television through different media (digital terrestrial television, satellite television, IPTV etc.). We will dissect the transport stream of digital television and get acquainted with different subtitle formats that are used today. After that, we will take a deeper look into the operation of the optical character recognition software library Tesseract OCR and get to know different procedures of identifying the text language. In conclusion of the master's thesis, we will build software that will separate all the subtitle traces from the digital television's stream and recognise the language of an individual trace.
Secondary keywords: digital television;optical character recognition;subtitles;language identification;IPTV;
URN: URN:SI:UM:
Type (COBISS): Master's thesis/paper
Thesis comment: Univ. v Mariboru, Fak. za Fak. za elektrotehniko, računalništvo in informatiko, Telekomunikacije
Pages: IX, 73 f.
ID: 10904542