prikaz prve stranice dokumenta Segmentacija panoramskih rendgenskih snimaka ljudske čeljusti
No public access
master's thesis
Segmentacija panoramskih rendgenskih snimaka ljudske čeljusti
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. urn:nbn:hr:168:756549
Šikić, Lucija
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Šikić, L. (2018). Segmentacija panoramskih rendgenskih snimaka ljudske čeljusti (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:756549

Šikić, Lucija. "Segmentacija panoramskih rendgenskih snimaka ljudske čeljusti." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:756549

Šikić, Lucija. "Segmentacija panoramskih rendgenskih snimaka ljudske čeljusti." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:756549

Šikić, L. (2018). 'Segmentacija panoramskih rendgenskih snimaka ljudske čeljusti', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 27 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:756549

Šikić L. Segmentacija panoramskih rendgenskih snimaka ljudske čeljusti [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2018 [cited 2024 December 27] Available at: https://urn.nsk.hr/urn:nbn:hr:168:756549

L. Šikić, "Segmentacija panoramskih rendgenskih snimaka ljudske čeljusti", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:168:756549

Metadata
TitleSegmentacija panoramskih rendgenskih snimaka ljudske čeljusti
Title (english)Segmentation of Panoramic X-Ray Images of Human Jaw
AuthorLucija Šikić
MentorMarko Subašić (mentor)
Committee memberMarko Subašić (predsjednik povjerenstva)
Committee memberSven Lončarić (član povjerenstva)
Committee memberTomislav Petković (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2018-07-13, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Razmatra se problem semantičke segmentacije panoramskih rendgenskih snimaka ljudske čeljusti. U tu su svrhu obrađene duboke konvolucijske neuronske mreže te su detaljno opisane metode i postupci za njihovo učenje. Definirani su problemi detekcije objekata i semantička segmentacija na razini primjerka. Za semantičku segmentaciju korištena je konvolucijska neuronska mreža koja paralelno detektira objekte i konstruira segmentacijske maske. Mreža je implementirana u radnoj okolini TensorFlow. Za njezino su učenje, validaciju i testiranje korišteni umjetno generirani snimci ljudske čeljusti. Na kraju su prikazani i rezultati segmentacije na stvarnim snimcima.
Abstract (english)
In this paper we are considering the problem of semantic segmentation of panoramic X-ray images of human jaw. In that purpose deep neural convolutional networks are shown and the methods and algorithms for their learning are explained in detail. The problems of object detection and instance segmentation are defined. Convolutional neural network, which detects objects and constructs segmentation masks in parallel, is used for semantic segmentation. Network is implemented using TensorFlow framework. It is learned, validated and tested on artificially generated images of human jaw. Following that, segmentation results on real images are presented.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:756549
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 on2019-03-14 01:14:36