prikaz prve stranice dokumenta ADAPTIVNI ALGORITMI ZA UKLANJANJE ŠUMA TEMELJENI NA PRESJECIŠTU INTERVALA POUZDANOSTI PRIMIJENJENI NA BIOMEDICINSKE SLIKE
Access restricted to students and staff of home institution
master's thesis
ADAPTIVNI ALGORITMI ZA UKLANJANJE ŠUMA TEMELJENI NA PRESJECIŠTU INTERVALA POUZDANOSTI PRIMIJENJENI NA BIOMEDICINSKE SLIKE
Rijeka: University of Rijeka, Faculty of Engineering, 2018. urn:nbn:hr:190:109921
Peić, Hajdi
University of Rijeka
Faculty of Engineering

Institutional repository: Repository of the University of Rijeka, Faculty of Engineering

Cite this document

Peić, H. (2018). ADAPTIVNI ALGORITMI ZA UKLANJANJE ŠUMA TEMELJENI NA PRESJECIŠTU INTERVALA POUZDANOSTI PRIMIJENJENI NA BIOMEDICINSKE SLIKE (Master's thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:109921

Peić, Hajdi. "ADAPTIVNI ALGORITMI ZA UKLANJANJE ŠUMA TEMELJENI NA PRESJECIŠTU INTERVALA POUZDANOSTI PRIMIJENJENI NA BIOMEDICINSKE SLIKE." Master's thesis, University of Rijeka, Faculty of Engineering, 2018. https://urn.nsk.hr/urn:nbn:hr:190:109921

Peić, Hajdi. "ADAPTIVNI ALGORITMI ZA UKLANJANJE ŠUMA TEMELJENI NA PRESJECIŠTU INTERVALA POUZDANOSTI PRIMIJENJENI NA BIOMEDICINSKE SLIKE." Master's thesis, University of Rijeka, Faculty of Engineering, 2018. https://urn.nsk.hr/urn:nbn:hr:190:109921

Peić, H. (2018). 'ADAPTIVNI ALGORITMI ZA UKLANJANJE ŠUMA TEMELJENI NA PRESJECIŠTU INTERVALA POUZDANOSTI PRIMIJENJENI NA BIOMEDICINSKE SLIKE', Master's thesis, University of Rijeka, Faculty of Engineering, accessed 24 December 2024, https://urn.nsk.hr/urn:nbn:hr:190:109921

Peić H. ADAPTIVNI ALGORITMI ZA UKLANJANJE ŠUMA TEMELJENI NA PRESJECIŠTU INTERVALA POUZDANOSTI PRIMIJENJENI NA BIOMEDICINSKE SLIKE [Master's thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2018 [cited 2024 December 24] Available at: https://urn.nsk.hr/urn:nbn:hr:190:109921

H. Peić, "ADAPTIVNI ALGORITMI ZA UKLANJANJE ŠUMA TEMELJENI NA PRESJECIŠTU INTERVALA POUZDANOSTI PRIMIJENJENI NA BIOMEDICINSKE SLIKE", Master's thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:190:109921

Metadata
TitleADAPTIVNI ALGORITMI ZA UKLANJANJE ŠUMA TEMELJENI NA PRESJECIŠTU INTERVALA POUZDANOSTI PRIMIJENJENI NA BIOMEDICINSKE SLIKE
Title (english)Denoising of X-ray Images Using the Adaptive Algorithm Based on the LPA-RICI Algorithm
AuthorHajdi Peić
MentorJonatan Lerga (mentor)
Committee memberKristijan Lenac (predsjednik povjerenstva)
GranterUniversity of Rijeka
Faculty of Engineering
Rijeka
Defense date and country2018-03, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
• Proučavanje recentne literature vezane uz postojeće metode uklanjanja šuma iz slike • Implementacija algoritma relativnog presjecišta intervala pouzdanosti u Matlabu • Sudjelovanje u implementaciji dvodimenzionalne inačice predloženog algoritma za obradu slike • Implementacija tri adaptivne inačice algoritma za uklanjanje šuma iz slike u Matlabu: - 2D LPA-RICI algoritma s podesivim kvadrilateralnim regijama - 2D LPA-RICI algoritma s podesivim oktagonalnim regijama - 2D LPA-RICI algoritma s podesivim heksadekagonalnim regijama • Usporedba rezultata dobivenih za sve tri inačice algoritma • Usporedba rezultata dobivenih korištenjem adaptivnog 2D LPA-RICI algoritma s rezultatima dobivenim korištenjem fiksnih širina otvora • Usporedba rezultata dobivenih korištenjem adaptivnog 2D LPA-RICI algoritma s rezultatima dobivenim korištenjem postupka temeljenog na Gaussovom uglađivanju • Analiziranje računalne zahtjevnosti i vremena izvršavanja algoritma za sve tri inačice predložene adaptivne 2D LPA-RICI metode
Abstract (english)
An adaptive method for MRI image denoising was proposed in the paper. The method is based on a modification of the ICI algorithm called the RICI algorithm. The RICI algorithm was further extended to 2D image denoising. The 2D LPA-ICI method was shown to increase PSNRs of denoised MRI images by up to 7.11 dB when compared to noisy images outperforming fixed size filtering by up to 5.89 dB. In contrast, the 2D LPA-RICI method was shown to increase PSNRs of denosied MRI images by up to 7.75 dB when compared to the noisy image, outperforming the 2D LPA-ICI method by up to 1.32 dB and fixed size filtering by up to 6.48 dB. This improvement is caused by calculating the size and shape of 2D regions locally and independently for each image pixel. Thus, the method is easy to parallelize in order to reduce its execution time. Furthermore, three types of the adaptive regions (quadrilateral, octagonal and hexakaidecagonal) were tested showing that the larger number of polygonal angles in adaptive 2D regions does not necessarily lead to significant improvements in image denoising quality. However, for all three types of regions and all tested noise levels, the 2D LPA-RICI method outperformed other tested methods (fixed size filtering and the adaptive ICI based method).
Keywords
Languagecroatian
URN:NBNurn:nbn:hr:190:109921
Study programmeTitle: Computer Engineering
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 conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2018-04-09 09:08:32