Raspoznavanje tiskanih znakova

undergraduate thesis

• Title (english): Optical character recognition
• Author: Bojana Savić
• Mentor: Tomislav Hrkać (mentor)
• Committee member: Tomislav Hrkać (predsjednik povjerenstva)
• Committee member: Zvonimir Pavlić (član povjerenstva)
• Committee member: Darijan Marčetić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2014-07-14, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Jedna od vrlo važnih primjena računalnog vida je kompjutersko raspoznavanje teksta. U ovom radu je opisan jedan malo drugačiji pristup raspoznavanju teksta od standardnih metoda za ovu problematiku pomoću karakterističnih kuteva svakog pojedinog znaka abecede. Dan je prikaz rezultata za font (arial) za koji je metoda optimirana, kao i rezultati testa na 6 različitih fontova koji nisu upotrebljeni u učenju raspoznavanja originalnog fonta. Metoda je također testirana na otpornost prepoznavanja na deformacije slike. Dan je kratki osvrt na rezultate kao i eventualna dalnja poboljšanja algoritma u smislu boljeg raspoznavanja znakova i poboljšanja brzine rada algoritma.

Abstract (english)

Recognition of printed text via a computer is an important implementation of computer vision. In this work was given a bit different approach to the standard methods used for solving this problem using characteristic angles of each character of the alphabet. The results were given for font (Arial) for which the method was optimized to work with, as well as the results for recognition 6 other fonts which were not used as sample for the process of computer learning. The proposed method was also tested for tolerance on deformation of character picture. In the end was given a short elaboration on the results and were proposed potential adjustments of the algorithm for better recognition of characters and the overall speed of the algorithm.

• Keywords: raspoznavanje znakova; tekst; karakteristični kutevi; različiti fontovi; deformacije slike
• Keywords (english): character recognition; text; characteristic angles; different fonts; picture deformation
• Language: croatian
• URN:NBN: urn:nbn:hr:168:028182
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-05 17:53:30