prikaz prve stranice dokumenta Segmentacija jezgara stanica primjenom Mask R-CNN arhitekture
Access restricted to authenticated users
undergraduate thesis
Segmentacija jezgara stanica primjenom Mask R-CNN arhitekture
Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. urn:nbn:hr:179:301236
Vinčić, Emil
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Electronics and Computing

Institutional repository: Repository of the Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture

Cite this document

Vinčić, E. (2022). Segmentacija jezgara stanica primjenom Mask R-CNN arhitekture (Undergraduate thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:301236

Vinčić, Emil. "Segmentacija jezgara stanica primjenom Mask R-CNN arhitekture." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:301236

Vinčić, Emil. "Segmentacija jezgara stanica primjenom Mask R-CNN arhitekture." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:301236

Vinčić, E. (2022). 'Segmentacija jezgara stanica primjenom Mask R-CNN arhitekture', Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 02 December 2024, https://urn.nsk.hr/urn:nbn:hr:179:301236

Vinčić E. Segmentacija jezgara stanica primjenom Mask R-CNN arhitekture [Undergraduate thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2022 [cited 2024 December 02] Available at: https://urn.nsk.hr/urn:nbn:hr:179:301236

E. Vinčić, "Segmentacija jezgara stanica primjenom Mask R-CNN arhitekture", Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:179:301236

Metadata
TitleSegmentacija jezgara stanica primjenom Mask R-CNN arhitekture
Title (english)Nuclei Cell Segmentation Using the Mask R-CNN Architecture
AuthorEmil Vinčić
MentorMatko Šarić https://orcid.org/0000-0001-9752-9653 (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2022-09-22, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom radu predstavljene su suvremene arhitekture za detekciju i segmentaciju objekata na slikama primjenom dubokog učenja. Na početku su izneseni i pojašnjeni osnovni pojmovi vezani za područje strojnog učenja i njegovog potpodručja dubokog učenja. Objašnjena je konstrukcija i djelovanje umjetnih i dubokih neuronskih mreža s dubljim uvidom u kategoriju konvolucijskih dubokih neuronskih mreža. Potom je prikazana primjena navedene kategorije mreža pri prepoznavnju objekata, odnosno klasifikaciji i lokalizaciji slike. Na to se nadovezuje tema detekcije objekata pri čemu su objašnjene suvremene arhitekture temeljene na konvolucijskim neuronskim mrežama, a to su R-CNN, Fast R-CNN, Faster R-CNN i Mask R-CNN. Tema segmentacije slike koja predstavlja nastavak procesa prepoznavanja i detekcije je pritom objašnjena nakon čega se detaljnije obrazlaže tema segmentacije stanica u mikroskopskim slikama. Opisane su i analizirane metode za segmentaciju jezgara stanica pri čemu je najviše predstavljena Mask R-CNN arhitektura.
Abstract (english)
This paper presents modern architectures for the detection and segmentation of objects in images using deep learning. At the beginning, the basic terms related to the field of machine learning and its subfield of deep learning were presented and reinforced. The construction and operation of artificial and deep neural networks is explained with a deeper insight into the category of convolutional deep neural networks. Then, the application of the mentioned network category in object recognition, i.e. classification and image localization, is shown. This is followed by the topic of object detection, where modern architectures based on convolutional neural networks, namely R-CNN, Fast R-CNN, Faster R-CNN and Mask R-CNN, are explained. The topic of image segmentation, which is a continuation of the process of recognition and detection, is explained, after which the topic of cell segmentation in microscopic images is explained in more detail. Methods for segmentation of cell nuclei are described and analyzed, with the Mask R-CNN architecture being the most presented.
Keywords
Languagecroatian
URN:NBNurn:nbn:hr:179:301236
Study programmeTitle: Computing
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to authenticated users
Terms of useLicence In copyright icon
Created on2023-10-04 10:38:17