Duboke neuronske mreže za analizu slika očne pozadine

undergraduate thesis

• Title (english): Deep neural networks for retinal image analysis
• Author: Jure Žuljević
• Mentor: Sven Lončarić (mentor)
• Committee member: Sven Lončarić (predsjednik povjerenstva)
• Committee member: Pavle Prentašić (član povjerenstva)
• Committee member: Nikola Banić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2016-07-11, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U radu su predstavljene umjetne neuronske mreže i njihovo proširenje duboke neuronske mreže. Opisan je način rada, izgled arhitekture koja je korištena te su predstavljeni eksperimentalni rezultati. Cilj ovog rada bilo je segmentiranje krvnih žila iz slika očne pozadine. Za rad s mrežom korišten je radni okvir Caffe, dane su upute za njegovu instalaciju, objašnjeno korištenje te opisani njegovi slojevi i parametri. Na kraju su predočeni dobiveni rezultati s opisima i slikama

Abstract (english)

This paper describes an artificial neural networks and their expansion, deep neural networks. In this article it is described mode, architecture layout that has been used, and experimental results were presented. The aim of this work was the segmentation of the blood vessels of the retina images. Caffe framework was used to operate with neural networks. In article instructions for its installation were given, way to use explained and its layers and parameters described. Finally, the results were presented with descriptions and pictures.

• Keywords: umjetna neuronska mreža; konvolucijaska neuronska mreža; duboke neuronske mreže; mrežnica; očna pozadina; Caffe; Google Protocol Buffer
• Keywords (english): artificial neural network; convolutional neural network; deep neural network; retinal image; retina; Caffe; Google Protocol Buffer
• Language: croatian
• URN:NBN: urn:nbn:hr:168:706561
• Study programme: Title: 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 resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 14:38:17