prikaz prve stranice dokumenta Metode za poboljšanje kvalitete slika u boji
No public access
master's thesis
Metode za poboljšanje kvalitete slika u boji
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. urn:nbn:hr:168:994857
Pivac, Lana
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Pivac, L. (2022). Metode za poboljšanje kvalitete slika u boji (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:994857

Pivac, Lana. "Metode za poboljšanje kvalitete slika u boji." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. https://urn.nsk.hr/urn:nbn:hr:168:994857

Pivac, Lana. "Metode za poboljšanje kvalitete slika u boji." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. https://urn.nsk.hr/urn:nbn:hr:168:994857

Pivac, L. (2022). 'Metode za poboljšanje kvalitete slika u boji', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 19 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:994857

Pivac L. Metode za poboljšanje kvalitete slika u boji [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2022 [cited 2024 December 19] Available at: https://urn.nsk.hr/urn:nbn:hr:168:994857

L. Pivac, "Metode za poboljšanje kvalitete slika u boji", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:168:994857

Metadata
TitleMetode za poboljšanje kvalitete slika u boji
Title (english)Methods for quality enhancement of color images
AuthorLana Pivac
MentorSonja Grgić (mentor)
Committee memberSonja Grgić (predsjednik povjerenstva)
Committee memberMarko Bosiljevac (član povjerenstva)
Committee memberDario Bojanjac (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2022-07-19, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Kvaliteta slike se vrlo lako narušava lošom rasvjetom, vremenskim uvjetima ili opremom korištenom za stvaranje same slike. Takvi uvjeti dovode do nedostatka informacija u slikama. Kako bi se taj problem riješio, razvijene su razne metode poboljšanja kvalitete slike koje oporavljaju izgubljene informacije. Osnovna podjela takvih metoda je na temelju prostorne i frekvencijske domene. U ovome radu opisano je po nekoliko metoda za obje domene, a one uključuju rastezanje kontrasta, izjednačavanje histograma, izoštravanje i zaglađivanje slike te homomorfno filtriranje. Pored tih metoda, ukratko su opisane i metode temeljene na dubokom učenju. Zatim je detaljnije opisana Retinex teorija kao i primjeri metoda zasnovanih na njoj. Rad se može podijeliti na teorijski i praktični dio. U teorijskom su dijelu opisane matematičke formule i algoritmi pomoću kojih se izvršavaju navedene metode. Zatim slijedi praktični dio u kojem je prikazan dio programskih rješenja, napisanih u programskom jeziku Python, te rezultati testiranja slika i njihova usporedba.
Abstract (english)
Image quality is very easily affected by lightning, weather conditions or equipment that was used to capture the image. Those conditions lead to information loss in images. In order to solve this problem, various image quality enhancement methods that recover information loss have been created. The main division of those methods is based on spatial domain and frequency domain. This paper presents a few methods for both of those domains, and some of them include contrast stretching, histogram equalization, image sharpening, image smoothing and homomorphic filtering. In addition to these methods, methods based on deep learning are briefly described. Then there is a more detail description of Retinex theory and methods based on it. This paper can be split into a theoretical and practical part. Theoretical part contains mathematical formulas and algorithms which are crucial for these methods to work. This is followed by practical part in which part of programming solutions written in Python programming language are shown, as well as the results of testing images and their comparison.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:994857
Study programmeTitle: Computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2023-01-13 15:53:44