Očitavanje rukom pisanih decimalnih brojeva temeljeno na dubokim modelima

master's thesis

• Title (english): Deep Models Based Recognition of Decimal Numbers
• Author: Stjepan Dugonjić
• Mentor: Marko Čupić (mentor)
• Committee member: Marko Čupić (predsjednik povjerenstva)
• Committee member: Željka Mihajlović (član povjerenstva)
• Committee member: Domagoj Jakobović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2019-07-10, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Problemi analize i obrade slike dio su brojnih grana ljudske djelatnosti. Poseban izazov predstavljaju problemi u kojima se sa slike nastoji očitati rukom pisani tekst. U ovom se radu razmatra segmentacijski pristup očitavanju takvih znakova pomoću dubokih modela. Ispituje se sposobnost takvog sustava na konkretnom primjeru očitavanja rukom pisanih decimalnih brojeva. Prikazani su i komentirani dobiveni rezultati te je dan kratak opis funkcionalnosti razvijenog grafičkog sučelja.

Abstract (english)

Image analysis and processing problems are present in numerous human activities. Most challenging ones involve optical character recognition, specifically recognition of handwritten characters. This thesis covers segmentation-based approach to that kind of problems using the power of deep models. Capabilities of such systems are tested on real problem that involves recognition of handwritten decimal numbers. Results are shown and commented and short description of developed graphical user interface is presented.

• Keywords: očitavanje znakova; segmentacija; duboki modeli; neuronske mreže; konvolucija; autoenkoder
• Keywords (english): optical character recognition; segmentation; deep models; neural networks; convolution; autoencoder
• Language: croatian
• URN:NBN: urn:nbn:hr:168:262525
• 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: 2020-01-07 17:44:10