Detekcija registarskih tablica u slikama vozila

undergraduate thesis

• Title (english): Detection of License Plates in Vehicle Images
• Author: Antonio Vencl
• Mentor: Tomislav Hrkać (mentor)
• Committee member: Tomislav Hrkać (predsjednik povjerenstva)
• Committee member: Marko Barišić (član povjerenstva)
• Committee member: Franjo Matković (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

Na početku rada sam dao kratki uvod u povijest razvoja umjetne inteligencije na primjeru šaha, te sam predstavio temu ovoga rada.
Zatim slijedi kratki uvod u umjetne neuronske mreže gdje sam probao povezati matematički neuron s biološkim, nakon toga je ukratko opisana arhitektura i rad konvolucijskih neuronskih mreža. Zatim je dan kratki opis korištenih tehnologija kao što su Darknet, YOLOv3, LabelIMG, nakon čega je opisan ulazni skup podataka i što se u njemu nalazi. Na kraju je ukratko opisan način treniranja i izneseni su rezultati ispitani na testnom skupu.

Abstract (english)

At the beginning of the paper I gave a brief introduction to the history of the development of artificial intelligence on the example of chess, and I presented the topic of this paper.
Then follows a brief introduction to artificial neural networks where I tried to connect a mathematical neuron with a biological one, followed by a brief description of the architecture of convolutional neural networks. Then, a short description of used technologies such as Darknet, YOLOv3, LabelIMG is given, after which the input data set and what is in it is described. At the end, the method of training is briefly described and the results on a test set are presenetd.

• Keywords: Umjetne neuronske mreže; konvolucijske neuronske mreže; strojno učenje; YOLOv3; registracijska tablica; vozilo
• Keywords (english): Artificial neural network; convolutional neural networks; machine learning; YOLOv3; registration label; vehicle
• Language: croatian
• URN:NBN: urn:nbn:hr:168:055544
• 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: 2023-01-14 21:54:55