Prepoznavanje znakova primjenom neuronskih mreža

undergraduate thesis

• Title (english): Recognition of Symbols Using Neural Networks
• Author: Alen Papak
• Mentor: Goran Delač (mentor)
• Committee member: Goran Delač (predsjednik povjerenstva)
• Committee member: Adrian Satja Kurdija (član povjerenstva)
• Committee member: Davor Vukadin (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-05, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu opisane su umjetne neuronske mreže, konvolucijske neuronske mreže i osnovni pojmovi vezani uz iste. Uz rad je razvijena konvolucijska neuronska mreža za prepoznavanje rukom pisanih brojki i velikih slova engleske abecede. Mreža je učena na primjerima iz baze rukom pisanih znakova NIST Special Database 19. Skup primjera je prije korištenja prošao predobradu. Razvijeno je i grafičko korisničko sučelje za klasifikaciju znakova. Na kraju su opisani rezultati ispitivanja neuronske mreže.

Abstract (english)

This work describes artificial neural networks, convolutional neural networks and basic concepts related to them. As a part of this work, a convolutional neural network for classification of handwritten digits and capital letters of English alphabet is made. Network is trained on examples from handwritten character base NIST Special Database 19. Dataset underwent preprocessing before usage. A graphical user interface for classification of symbols was developed. In the end the results of neural network testing were described.

• Keywords: umjetne neuronske mreže; konvolucijske neuronske mreže; računalni vid; prepoznavanje rukom pisanih znakova; predobrada; NIST Special Database 19; Keras
• Keywords (english): artificial neural networks; convolutional neural networks; computer vision; handwritten symbol recognition; preprocessing; NIST Special Database 19; Keras
• Language: croatian
• URN:NBN: urn:nbn:hr:168:082938
• 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: 2023-01-15 10:57:44