Postupci rekolorizacije slika

master's thesis

• Title (english): Image Colorization Methods
• Author: Adi Čaušević
• Mentor: Marko Čupić (mentor)
• Committee member: Marko Čupić (predsjednik povjerenstva)
• Committee member: Željka Mihajlović (član povjerenstva)
• Committee member: Siniša Šegvić (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

U ovome radu opisana su tri pristupa kolorizaciji crno-bijelih slika. Za sve pristupe kolorizacija korištene su umjetne neuroneke mreže, te je za svaki od modela predstavljena je arhitektura, način rada, rezultati, te mane i moguća poboljšanja modela i/ili procesa treniranja. Prije opisa modela pokrivene su osnove dubokoga učenja potrebne za razumijevanje opisanih modela.

Abstract (english)

In this thesis, three different approaches to the colorization of grayscale photographs were described. Every approach used artificial neural networks as the colorizer. The architecture, learning process, results, and the flaws and possible improvements were presented for each of the models. Before the models were described, an overview of deep learning concepts and methods needed for the understanding of the used models was provided.

• Keywords: kolorizacija; crno-bijele slike; CNN; GAN; U-Net; image-to-image
• Keywords (english): colorization; grayscale images; CNN; GAN; U-Net; image-to-image
• Language: english
• URN:NBN: urn:nbn:hr:168:591347
• 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 14:44:18