Download
PDF 133.17 KB
master's thesis
24   11
Image quality evaluation by using DIIVINE metric
Želimir Janković (2015)
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Communications
Chair of Radiocommunications and Telecommunications
Metadata
TitleOcjena kvalitete slike DIIVINE metrikom
AuthorŽelimir Janković
Mentor(s)Mario Vranješ (thesis advisor)
Abstract
U radu je dana teorijska podloga vezana za procjenu kvalitete slike. Procjena kvalitete slike igra vrlo važnu ulogu u vizualnoj komunikaciji. Detaljno je analizirana i opisana DIIVINE metrika za procjenu kvalitete mirne slike. Napravljena je usporedba rezultata DIIVINE metrike s PSNR i SSIM metrikama. Rezultati su dobiveni pomoću programskog paketa Matlab. Za vrednovanje rezultata izračunat je Pearsonov linearni koeficijent korelacije. DIIVINE metrika se pokazala usporedivom s PSNR i SSIM metrikama, iako za ocjenu kvalitete ne koristi referentnu sliku.
Keywordsimage quality assessment objective image quality metrics DIIVINE PSNR SSIM LIVE database VCL@FER database
Parallel title (English)Image quality evaluation by using DIIVINE metric
Committee MembersMario Vranješ (committee chairperson)
Snježana Rimac-Drlje (committee member)
Denis Vranješ (committee member)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Lower level organizational unitsDepartment of Communications
Chair of Radiocommunications and Telecommunications
PlaceOsijek
StateCroatia
Scientific field, discipline, subdisciplineTECHNICAL SCIENCES
Electrical Engineering
Telecommunications and Informatics
Study programme typeuniversity
Study levelgraduate
Study programmeGraduate University Study Programme in Electrical Engineering; branch: Communications and Informatics, Power Engineering
Study specializationbranch: Communications and Informatics
Academic title abbreviationmag.ing.el.
Genremaster's thesis
Language Croatian
Defense date2015-10-01
Parallel abstract (English)
In this work, the theory related to image quality assessment is given. Image quality assessment (IQA) plays an important role in visual communication. DIIVINE metric for IQA is analyzed in detail. Comparison of results between DIIVINE, PSNR and SSIM is made. The results were obtained using Matlab. For evaluation of the results the Pearson linear correlation coefficient is calculated. DIIVINE metric provided results comparable to PSNR and SSIM metrics, although it does not use the reference image for quality evaluation.
Parallel keywords (Croatian)ocjena kvalitete mirne slike objektivne metrike DIIVINE PSNR SSIM LIVE baza VCL@FER baza
Resource typetext
Access conditionOpen access
Terms of usehttp://rightsstatements.org/vocab/InC/1.0/
URN:NBNhttps://urn.nsk.hr/urn:nbn:hr:200:847899