| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:OPTIČNO RAZPOZNAVANJE ZNAKOV IZ SLIK IN VIDEA
Authors:ID Štraser, Aljaž (Author)
ID Holobar, Aleš (Mentor) More about this mentor... New window
Files:.pdf UNI_Straser_Aljaz_2012.pdf (1,63 MB)
MD5: 232F801EEE49B5A3BF88EAB6F6339FAE
PID: 20.500.12556/dkum/6ac74ddf-e255-4e9a-a220-0cb525fa2c2d
 
Language:Slovenian
Work type:Bachelor thesis/paper
Typology:2.11 - Undergraduate Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:V diplomskem delu obravnavamo optično razpoznavo znakov iz slik in videa. Teoretični del obsega študijo procesa optične razpoznave znakov, kjer analiziramo vse pomembne korake predobdelave slik, detekcije besedila in razpoznave znakov. Praktični del obsega izdelavo aplikacije v okolju .NET, kjer najprej z uporabo knjižnice Emgu CV implementiramo algoritma za detekcijo orientacije besedila in izločitev besedila iz ozadja ter ostalih nepotrebnih grafičnih elementov. Predobdelane slike z besedilom nato obdelamo s prostodostopnim sistemom za optično razpoznavo znakov Tesseract OCR, za katerega izdelamo tudi podporo razpoznavi znakov slovenskega črkopisa. Razpoznavalnik Tesseract OCR preko ovoja .NET Emgu.CV.OCR vključimo v našo aplikacijo.
Keywords:Optično razpoznavanje znakov, Obdelava slik, Emgu CV, Tesseract OCR, ogrodje .NET
Place of publishing:Maribor
Publisher:[A. Štraser]
Year of publishing:2012
PID:20.500.12556/DKUM-37844 New window
UDC:004.352.242:621.397.4(043.2)
COBISS.SI-ID:16493078 New window
NUK URN:URN:SI:UM:DK:B1NCVK3D
Publication date in DKUM:27.11.2012
Views:2207
Downloads:194
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Secondary language

Language:English
Title:OPTICAL CHARACTER RECOGNITION FROM PICTURES AND VIDEO
Abstract:The thesis discusses optical character recognition from images and video frames. The theoretical part of the thesis analyises the main steps of image preprocessing, text detection and character recognition. The practical part of the thesis describes developement of an application for optical recognition of arbitrarily oriented text in .NET framework. We use the Emgu CV library to implement the algorythm for automatic detection and compensation of text orientation and the algorithm for text extraction from background and other nontextual graphic elements. The output of these preprocessing steps is fed into the open-source Tesseract OCR engine for optical character recognition. We upgrade the Tesseract OCR with the support for specific charachters in Slovenian language and include it into our application through the Emgu.CV.OCR .NET wrapper.
Keywords:Optical character recognition, Processing images, Emgu CV, Tesseract OCR, .NET Framework


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica