prikaz prve stranice dokumenta Utjecaj pred-obrade slike na algoritam za detekciju karcinoma mokraćnog mjehura
Access restricted to students and staff of home institution
master's thesis
Utjecaj pred-obrade slike na algoritam za detekciju karcinoma mokraćnog mjehura
Rijeka: University of Rijeka, Faculty of Engineering, 2018. urn:nbn:hr:190:837835
Lorencin, Ivan
University of Rijeka
Faculty of Engineering
Department of Automation and Electronics
Section of Electronics, Robotics and Automation

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

Cite this document

Lorencin, I. (2018). Utjecaj pred-obrade slike na algoritam za detekciju karcinoma mokraćnog mjehura (Master's thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:837835

Lorencin, Ivan. "Utjecaj pred-obrade slike na algoritam za detekciju karcinoma mokraćnog mjehura." Master's thesis, University of Rijeka, Faculty of Engineering, 2018. https://urn.nsk.hr/urn:nbn:hr:190:837835

Lorencin, Ivan. "Utjecaj pred-obrade slike na algoritam za detekciju karcinoma mokraćnog mjehura." Master's thesis, University of Rijeka, Faculty of Engineering, 2018. https://urn.nsk.hr/urn:nbn:hr:190:837835

Lorencin, I. (2018). 'Utjecaj pred-obrade slike na algoritam za detekciju karcinoma mokraćnog mjehura', Master's thesis, University of Rijeka, Faculty of Engineering, accessed 10 November 2024, https://urn.nsk.hr/urn:nbn:hr:190:837835

Lorencin I. Utjecaj pred-obrade slike na algoritam za detekciju karcinoma mokraćnog mjehura [Master's thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2018 [cited 2024 November 10] Available at: https://urn.nsk.hr/urn:nbn:hr:190:837835

I. Lorencin, "Utjecaj pred-obrade slike na algoritam za detekciju karcinoma mokraćnog mjehura", Master's thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:190:837835

Metadata
TitleUtjecaj pred-obrade slike na algoritam za detekciju karcinoma mokraćnog mjehura
Title (english)Influence of Image Pre-Editing on Algorithm for Urinary Bladder Cancer Detection
AuthorIvan Lorencin
MentorZlatan Car (mentor)
Committee memberViktor Sučić (predsjednik povjerenstva)
Committee memberLivio Šušnjić (član povjerenstva)
Committee memberAndrea Andrijašević (član povjerenstva)
GranterUniversity of Rijeka
Faculty of Engineering
(Department of Automation and Electronics)
(Section of Electronics, Robotics and Automation)
Rijeka
Defense date and country2018-10-05, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Shipbuilding
Abstract
U ovom su radu realizirane dvije metode detekcije karcinoma mokraćnog mjehura pomoću slike. U prvom su djelu prikazane metode za predobradu slike, koje se sastoje od: augmentacije, skaliranja slike, Canny detektora ruba, detektora ruba realiziranog pomoću Laplaciana te fourierova transformacija. U sljedećem je koraku realizirana neuronska mreža, na kojoj se izvršilo ispitivanje utjecaja navedenih metoda za pred-obradu slike. Iz dobivenih je rezultata vidljivo kako mreža postiže najveću točnost ukoliko su provedeni skaliranje i augmentacije, dok se uz upotrebu detektora ruba smanjuje točnost ali i povećava brzina treniranja. Ukoliko se koristi genetsko programiranje postižu se zadovoljavajuće točnosti jedino uz augmentirani set podataka za treniranje.
Abstract (english)
In this paper, two methods of detecting bladder cancer are described. In the first part, the methods of image pre-editing, consisting of: augmentation, image scaling, Canny edge detector and edge detectors realized by Laplacian are shown. In the next step, a neural network was realized, which tested the influence of the above pre-processing methods. The obtained results show that the network achieves the highest accuracy if scaling and augmentation are performed, while using the edge detector decreases the accuracy but also increases the training speed. If genetic programming is used, higher accuracy is achieved only with the augmented training data set.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:190:837835
Study programmeTitle: Electrical Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka elektrotehnike (magistar/magistra inženjer/inženjerka elektrotehnike)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2018-10-17 12:57:25