Thesis Details

Rozpoznávač psaného textu pro mobilní telefony

Master's Thesis Student: Talaš Vladimír Academic Year: 2006/2007 Supervisor: Schwarz Petr, Ing., Ph.D.
English title
Recognition of Handwriting for Mobile Phones
Language
Czech
Abstract

The goal of this project is to create a mobile phone application, which can use phone camera to get a photography. This photography contains text, application has an ability to find a text, recognize all characters and send output as SMS. In this application there are implemented algorithms for text recognize from pictures based on Hidden Markovov Models. The particular stress is put on training of the model, to maximalise a succes of text recognition. There are some experiments model training with model variables, which are leading in better ability of text recognition. It was achieved a value of 97% succesfully recognized characters.

Keywords

OCR, text recognition, Hidden Markovov Models, mobile phone, java, J2ME, Symbian

Department
Department of Computer Graphics and Multimedia FIT BUT
Degree Programme
Electrical Engineering and Computer Science, Field of Study Computer Science and Engineering
Files
Status
defended, grade E
Date
21 June 2007
Reviewer
Chalupníček Kamil, Ing.
Committee
Dvořák Václav, prof. Ing., DrSc. (DCSY FIT BUT), předseda
Burget Radek, doc. Ing., Ph.D. (DIFS FIT BUT), člen
Eysselt Miloš, Ing., CSc. (DCSY FIT BUT), člen
Hanáček Petr, doc. Dr. Ing. (DITS FIT BUT), člen
Janoušek Vladimír, doc. Ing., Ph.D. (DITS FIT BUT), člen
Vondrák Ivo, prof. Ing., CSc. (FEI VSB), člen
Citation
TALAŠ, Vladimír. Rozpoznávač psaného textu pro mobilní telefony. Brno, 2007. Master's Thesis. Brno University of Technology, Faculty of Information Technology. 2007-06-21. Supervised by Schwarz Petr. Available from: https://www.fit.vut.cz/study/thesis/5813/
BibTeX 
@mastersthesis{FITMT5813,
    author = "Vladim\'{i}r Tala\v{s}",
    type = "Master's thesis",
    title = "Rozpozn\'{a}va\v{c} psan\'{e}ho textu pro mobiln\'{i} telefony",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2007,
    location = "Brno, CZ",
    language = "czech",
    url = "https://www.fit.vut.cz/study/thesis/5813/"
}

Theses

Back to top