Očitavanje rukom pisanih identifikacijskih brojeva temeljeno na strojnom učenju

master's thesis

• Title (english): Machine Learning Based Recognition of Student Identifiers
• Author: Domagoj Latečki
• Mentor: Marko Čupić (mentor)
• Committee member: Marko Čupić (predsjednik povjerenstva)
• Committee member: Alan Jović (član povjerenstva)
• Committee member: Marin Golub (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-08, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu razmatran je problem raspoznavanja rukom pisanih studentskih identifikacijskih brojeva. Proučeno je područje raspoznavanja teksta te je opisan kratak pregled tog područja. Opisana je struktura korištene neuronske mreže i algoritma za učenje te su navedene njihove formule i izvodi. Također su navedeni i opisani svi koraci implementiranog sustava za raspoznavanje te je provedena analiza rezultata točnosti raspoznavanja rukom pisanih brojeva. Donesen je zaključak o komponentama sustava... More koje je potrebno poboljšati kako bi se dobila veća točnost raspoznavanja. Less

Abstract (english)

This thesis considers the problem of recognition of handwritten student identifier numbers. The field of text recognition has been examined and a short overview is given. A description of the used neural network structure and learning algorithm is given as well as their formulas and mathematical derivations. Every step of the implemented recognition system is described along with the analysis of the results of handwritten digit recognition. A conclusion is presented about which components of... More the system should be improved in order to achieve better accuracy of digit recognition. Less

• Keywords: Raspoznavanje rukom pisanih znamenaka; Raspoznavanje teksta; Neuronska mreža; Gradijentni spust
• Keywords (english): Handwritten digit recognition; Text recognition; Neural network; Gradient descent
• Language: croatian
• URN:NBN: urn:nbn:hr:168:434432
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 09:14:59