Raspoznavanje objekata uporabom umjetnih neuronskih mreža

undergraduate thesis

• Title (english): Object Recognition by Using Artificial Neural Networks
• Author: Dominik Prester
• Mentor: Zoran Kalafatić (mentor)
• Committee member: Zoran Kalafatić (predsjednik povjerenstva)
• Committee member: Darijan Marčetić (član povjerenstva)
• Committee member: Martin Soldić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2018-07-13, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Raspoznavanje objekata na slici problem je domene raspoznavanja uzoraka. Objekti na slici su reprezentirani uzorcima, a neuronske mreže rade na principu analiziranja i učenja uzoraka. Konvolucijske neuronske mreže posebna su vrsta neuronskih mreža za koje se pokazalo da jako dobro rješavaju ovakve probleme.

Abstract (english)

Object recognition problems fall under the pattern recognition domain. Objects on images are represented by patterns and neural networks are good at learning and recognizing patterns. Convolutional neural networks are a specific sort of artitifial neural networks that has shown good results at object recognition problems.

• Keywords: umjetne neuronske mreže; raspoznavanje objekata
• Keywords (english): artificial neural networks; object recognition
• Language: croatian
• URN:NBN: urn:nbn:hr:168:674482
• 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: 2019-03-14 00:12:00