Metoda za automatsko očitavanje ispitnih košuljica pomoću dubokog učenja

master's thesis

• Title (english): Method for Automatically Reading of Test Forms Using Deep Learning
• Author: Ante Ćurić
• Mentor: Marko Subašić (mentor)
• Committee member: Marko Subašić (predsjednik povjerenstva)
• Committee member: Davor Petrinović (član povjerenstva)
• Committee member: Tomislav Pribanić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-16, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Rad se bavi metodom automatskog očitavanje ispitnih košuljica pomoću dubokog učenja. Na početku rada se opisuju korišteni podatkovni skupovi, alati, mjere. U nastavku se opisuje rješenje te rezultati rada pojedinačnih mreža u svakom koraku metode automatskog očitavanja ispitnih košuljica te rezultati očitavanja košuljica dobiven integriranjem mreže iz svakog koraka.

Abstract (english)

This work addresses a method for automatically reading of test form using deep learning. The paper first describes used datasets, tools and metrics. The second part of the paper describes the solution and the results of individual neural networks in each step in the method of automatically reading of test forms and the results of all of the neural networks working together.

• Keywords: računalni vid; duboko učenje; strojno učenje; Faster-RCNN; ResNet; ispitne košuljice
• Keywords (english): computer vision; deep learning; machine learning; Faster R-CNN; ResNet; exam sheet
• Language: croatian
• URN:NBN: urn:nbn:hr:168:277009
• 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 14:47:24