Usporedba algoritama za OCR pri različitim rezolucijama

master's thesis

• Author: Mario Mikšić
• Mentor: Darko Agić (mentor)
• Committee member: Darko Agić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Graphic Arts; Zagreb
• Defense date and country: 2012-12-5, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Graphic Technology

Abstract

Optičko prepoznavanje znakova (OCR) je kombinacija mehaničke i elektoničke

komunikacije za prijenos rukom pisanih ili otisnutih tekstova u računalni kod pomoću

optičkih uređaja. Njegova povijest seže i sto godina unazad i do danas se razgranala tj.

dio je jedne široke skupine optičkog prepoznavanja.Primjena njegovih mogućnosti

dovela nas je do toga da nam se optičko prepoznavanje uvuklo u sve životne prostore

kao što su prepoznavanje poslovnih kartica,interaktivne igre novog doba,osobna

identifikacija itd.,a najzaslužniji za to su sve bolji algoritmi. Oni omogućavaju sve bržu

i precizniju obradu (unos,raščiščavanje i usporedbu)no uvijek postoji mogućnost razvoja

pogotovo kombinacijom više algoritama. Bitna stavka je da pri prepoznavanju algoritmi

zadrže mogućnost"gledanja"na sliku bez obzira na rezoluciju i transformaciju slike

(translataciju, kaliranje i rotaciju) tj. da stvori slikovne invarijacije i da se prepoznavanje

dovede do razine ljudskih osjetila.

Abstract (english)

Optical Character Recognition(OCR) is combination of mechanical and

electronic comunication for transmission of handwritten, typewritten or printed text into

machine-encoded text using optical devices. It's histry goes hundred years back and

today has become part of the group of optical recognition devices. Using it's

possibilities led us to point where we have optical recognition in every area of our lives

such as the recognition of business cards, interactive games of new age, personal

identification, etc., and most responsible for it's progress are algorithms. They allow

faster and more accurate processing (input, clearing and comparison), but there is

always possibility of more development, especially with the combination of two or

more algorithms. The important fact is that the algorithms for recognition keep the

possibility of "seeing" the image, regardless of image resolution and transformation

(translation, scaling and rotation)and to create image invariants and to bring recognition

to the level of human senses.

• Keywords: Optičko prepoznavanje; slikovne invarijacije; rezolucija
• Keywords (english): Optical recognition; Image invariants; moment; resolution
• Language: croatian
• URN:NBN: urn:nbn:hr:216:118405
• Study programme: Title: Graphic technology; specializations in: Graphic technology, Design of graphic products; Course: Graphic technology; Study programme type: university; Study level: graduate; Academic / professional title: sveučilišni/a magistar/magistra inženjer/inženjerka grafičke tehnologije (sveučilišni/a magistar/magistra inženjer/inženjerka grafičke tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2024-04-17 08:56:22