prikaz prve stranice dokumenta Performanse konvolucijskih neuronskih mreža na prometnim znakovima zemalja Europe
  Download
PDF 1.55 MB
master's thesis
Performanse konvolucijskih neuronskih mreža na prometnim znakovima zemalja Europe
Pula: University of Pula, 2023. urn:nbn:hr:137:735594
Mažar, Krešimir
University of Pula
Faculty of Informatics in Pula

Institutional repository: Digital Repository Juraj Dobrila University of Pula

Cite this document

Mažar, K. (2023). Performanse konvolucijskih neuronskih mreža na prometnim znakovima zemalja Europe (Master's thesis). Pula: University of Pula. Retrieved from https://urn.nsk.hr/urn:nbn:hr:137:735594

Mažar, Krešimir. "Performanse konvolucijskih neuronskih mreža na prometnim znakovima zemalja Europe." Master's thesis, University of Pula, 2023. https://urn.nsk.hr/urn:nbn:hr:137:735594

Mažar, Krešimir. "Performanse konvolucijskih neuronskih mreža na prometnim znakovima zemalja Europe." Master's thesis, University of Pula, 2023. https://urn.nsk.hr/urn:nbn:hr:137:735594

Mažar, K. (2023). 'Performanse konvolucijskih neuronskih mreža na prometnim znakovima zemalja Europe', Master's thesis, University of Pula, accessed 29 April 2024, https://urn.nsk.hr/urn:nbn:hr:137:735594

Mažar K. Performanse konvolucijskih neuronskih mreža na prometnim znakovima zemalja Europe [Master's thesis]. Pula: University of Pula; 2023 [cited 2024 April 29] Available at: https://urn.nsk.hr/urn:nbn:hr:137:735594

K. Mažar, "Performanse konvolucijskih neuronskih mreža na prometnim znakovima zemalja Europe", Master's thesis, University of Pula, Pula, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:137:735594

Metadata
TitlePerformanse konvolucijskih neuronskih mreža na prometnim znakovima zemalja Europe
Title (english)Convolutional neural networks performance on traffic signs of European countries
AuthorKrešimir Mažar
MentorGoran Oreški (mentor)
Committee memberNikola Tanković (član povjerenstva)
Committee memberGoran Oreški (član povjerenstva)
Committee memberTihomir Orehovački (predsjednik povjerenstva)
GranterUniversity of Pula
(Faculty of Informatics in Pula)
Pula
Defense date and country2023-09-12, Croatia
Scientific / art field,
discipline and subdiscipline		SOCIAL SCIENCES
Information and Communication Sciences
Information Systems and Information Science
Abstract
Rad se fokusira na analizu performansi konvolucijskih neuronskih mreža (CNN) na podacima prometnih znakova zemalja Europe. Specifično, istraživanje koristi trening skup podataka prometnih znakova jedne države i test skup podataka na drugim državama. Cilj istraživanja je procijeniti sposobnost generalizacije CNN modela pri klasifikaciji i prepoznavanju prometnih znakova različitih europskih zemalja. U radu se detaljno opisuje prikupljanje i pretprocesiranje podataka, izgradnja i treniranje CNN modela te evaluacija performansi modela kroz različite metrike. Rezultati istraživanja pružaju uvid u transferabilnost CNN modela na različite zemlje prometnih znakova te ukazuju na mogućnosti primjene takvih modela u stvarnim uvjetima prometne signalizacije.
Abstract (english)
This study focuses on analyzing the performance of Convolutional Neural Networks (CNNs) on traffic sign data from European countries. Specifically, the research utilizes a training dataset consisting of traffic signs from one country and a separate test dataset containing traffic signs from other countries. The objective is to evaluate the generalization ability of CNN models in classifying and recognizing traffic signs from different European countries. The paper provides detailed descriptions of data collection, preprocessing, CNN model construction and training, and performance evaluation using various metrics. The results of this study offer insights into the transferability of CNN models across different traffic sign datasets and highlight the potential applications of such models in real-world traffic signaling scenarios.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:137:735594
Study programmeTitle: Master in Informatics; specializations in: Master in Informatics, Master in Informatics, specialisation: teaching, Master in Informatics, Master in Informatics, specialisation: teaching
Course: Master in Informatics
Study programme type: university
Study level: graduate
Academic / professional title: MAGISTAR/MAGISTRA INFORMATIKE - MAG.INF. (MAGISTAR/MAGISTRA INFORMATIKE - MAG.INF.)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2023-09-13 10:59:28