Določanje slikovnega prostora umetniških slik s pomočjo računalniškega vida

diplomsko delo

Rožle Sterle (Author), Franc Solina (Mentor)

Abstract

V diplomski nalogi smo raziskovali, kako lahko s pomočjo računalniškega vida avtomatsko izluščimo informacijo o globini iz umetniških slik. Izdelani sta bili dve metodi, ki z različnimi principi računalniškega vida poskušata rekonstruirati tridimenzionalni prostor v umetninah. Prva metoda temelji na zaznavanju obrazov in matematičnih lastnostih perspektive. Druga metoda pa uporablja napredni model MiDaS, da iz umetnin generira globinske slike. Analiza je bila izvedena na 10484 slikah iz zbirke WikiArt. Narejena je bila tudi analiza rezultatov z različnimi algoritmi nenadzorovanega strojnega učenja in primerjava obeh metod, ki je pokazala, da je s svojimi mnogimi prednostmi boljša druga metoda.

Keywords

slikovni prostor;določanje slikovnega prostora;umetniške slike;tridimenzionalni prostor;strojno učenje;univerzitetni študij;diplomske naloge;

Data

Language:	Slovenian
Year of publishing:	2024
Typology:	2.11 - Undergraduate Thesis
Organization:	UL FRI - Faculty of Computer and Information Science
Publisher:	[R. Sterle]
UDC:	004.93:75.051(043.2)
COBISS:	189277187
Views:	55
Downloads:	4
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Determining the visual space of artistic paintings using computer vision
Secondary abstract:	In the thesis, we explored how computer vision can be used to automatically extract depth information from artistic images. Two methods were developed, which use different computer vision principles to attempt to reconstruct three-dimensional space in artworks. The first method is based on the detection of faces and mathematical properties of perspective. The second method utilizes the advanced MiDaS model to generate depth images from artworks. The analysis was carried out on 10,484 images from the WikiArt collection. An analysis of the results was also made using various unsupervised machine learning algorithms. Comparison of both methods showed that the second method, with its many advantages, is better.
Secondary keywords:	computer vision;defining the image space;pictorial space;artistic paintings;art;machine learning;computer and information science;diploma;Računalniški vid;Slike;Umetnost;Računalništvo;Univerzitetna in visokošolska dela;
Type (COBISS):	Bachelor thesis/paper
Study programme:	1000468
Embargo end date (OpenAIRE):	1970-01-01
Thesis comment:	Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages:	78 str.
ID:	23126092