Raspoznavanje objekata uporabom umjetnih neuronskih mreža

undergraduate thesis

• Title (english): Object Recognition by Using Artificial Neural Networks
• Author: Mihaela Bošnjak
• Mentor: Zoran Kalafatić (mentor)
• Committee member: Zoran Kalafatić (predsjednik povjerenstva)
• Committee member: Zvonimir Pavlić (član povjerenstva)
• Committee member: Ivan Krešo (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2017-09-13, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Ovaj rad opisuje teoriju iza rada neuronskih mreža i praktičnu uporabu na
konkretnom problemu. Raspoznavanje objekata je problem za koji je izrađena
neuronska mreža i opisan postupak izgradnje. Korišten je skup podataka COIL-20 koji se sastoji od 20 različitih objekata. Na kraju opisani rezultati i izgrađena
mreža.

Abstract (english)

This work gives an overview of neural network theory and shows how to build
simple neural networks. It takes a concrete problem and shows us guidelines
on how to build a neural network. The considered problem, from the area of
computer vision, is object recognition. COIL-20 is the dataset used for training
and testing the network. It contains twenty different objects. The constructed
network and the results of the testing are described at the end of the paper.

• Keywords: neuronske mreže; konvolucijske neuronske mreže; detekcija objekata; računalni vid; klasifikacija
• Keywords (english): neural networks; convolutional neural networks; multiclass classification; computer vision
• Language: croatian
• URN:NBN: urn:nbn:hr:168:047231
• 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: 2019-03-13 19:14:46