Primjena neuronskih mreža pri prepoznavanju slika

undergraduate thesis

• Title (english): Application of neural networks in image recognition
• Author: Maja Pečar
• Mentor: Ivan Dunđer (mentor)
• Committee member: Sanja Seljan (predsjednik povjerenstva)
• Committee member: Vjera Lopina (član povjerenstva)
• Committee member: Ivan Dunđer (član povjerenstva)
• Granter: University of Zagreb; Faculty of Humanities and Social Sciences; (Department of information and Communication sciences); Zagreb
• Defense date and country: 2021-09-21, Croatia
• Scientific / art field, discipline and subdiscipline: SOCIAL SCIENCES; Information and Communication Sciences

Abstract

Umjetne neuronske mreže, kao jedan od najuspješnijih pristupa obrade podataka, rastu u upotrebi unutar svih znanstvenih područja. Prepoznavanje slika jedna je od najpristupačnijih primjena neuronskih mreža. Cilj ovog završnog rada je prikazati teorijsku podlogu prepoznavanja slika uz pomoć primjene umjetnih neuronskih mreža kod strojnog učenja te primjena ranije navedene teorije u praksi. Prvi dio rada odnosi se na teorijski aspekt i razvoj neuronskih mreža, a drugi na njihovu praktičnu primjenu pri prepoznavanja slika.

Abstract (english)

Artificial neural networks, as one of the most successful approaches to data processing, grow in use in all the scientific areas. Image recognition is one of the most accessible applications of neural networks. The goal of this undergraduate thesis is to present the theoretical basis of image recognition with the help of the application of artificial neural networks in machine learning and the application of the aforementioned theory in practice. The first part of the thesis deals with the theoretical aspect and development of neural networks, whereas the second with their practical application in image recognition.

• Keywords: umjetne neuronske mreže; prepoznavanje slika; konvolucijske neuronske mreže; strojno učenje; duboko učenje
• Keywords (english): artificial neural networks; image recognition; convolutional neural networks; machine learning; deep learning
• Language: croatian
• URN:NBN: urn:nbn:hr:131:478733
• Study programme: Title: Information Sciences; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) informacijskih znanosti (sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) informacijskih znanosti)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2021-09-22 12:32:01