prikaz prve stranice dokumenta Učinkovitost različitih vrsta neuronskih mreža u klasificiranju grafičkih prikaza
  Download
PDF 1.45 MB
undergraduate thesis
Učinkovitost različitih vrsta neuronskih mreža u klasificiranju grafičkih prikaza
Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. urn:nbn:hr:200:514626
Kovačević, David
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Visual Computing

Institutional repository: Faculty of Electrical Engineering, Computer Science and Information Technology Osijek

Cite this document

Kovačević, D. (2023). Učinkovitost različitih vrsta neuronskih mreža u klasificiranju grafičkih prikaza (Undergraduate thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:514626

Kovačević, David. "Učinkovitost različitih vrsta neuronskih mreža u klasificiranju grafičkih prikaza." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. https://urn.nsk.hr/urn:nbn:hr:200:514626

Kovačević, David. "Učinkovitost različitih vrsta neuronskih mreža u klasificiranju grafičkih prikaza." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. https://urn.nsk.hr/urn:nbn:hr:200:514626

Kovačević, D. (2023). 'Učinkovitost različitih vrsta neuronskih mreža u klasificiranju grafičkih prikaza', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 14 May 2024, https://urn.nsk.hr/urn:nbn:hr:200:514626

Kovačević D. Učinkovitost različitih vrsta neuronskih mreža u klasificiranju grafičkih prikaza [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2023 [cited 2024 May 14] Available at: https://urn.nsk.hr/urn:nbn:hr:200:514626

D. Kovačević, "Učinkovitost različitih vrsta neuronskih mreža u klasificiranju grafičkih prikaza", Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:200:514626

Metadata
TitleUčinkovitost različitih vrsta neuronskih mreža u klasificiranju grafičkih prikaza
Title (english)Neural Networks Efficiency in Chart Image Classification
AuthorDavid Kovačević
MentorJosip Job (mentor)
Committee memberJosip Job (predsjednik povjerenstva)
Committee memberGoran Knežević (član povjerenstva)
Committee memberIvica Lukić (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Software Engineering)
(Chair of Visual Computing)
Osijek
Defense date and country2023-06-16, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
Duboke umjetne neuronske mreže danas su najpouzdaniji, najbrži, te najefektivniji način za rješavanje problema vezanog uz prepoznavanje slika. Korištenjem dubokih umjetnih neuronskih mreža omogućava se učenje mreže na velikoj količini podataka čije rezultate kasnije možemo upotrijebiti u analizi istih (npr. prepoznavanje lica osoba na aerodromima). U ovom radu opisane su osnovne stvari potrebne za razumijevanje umjetnih neuronskih mreža te je opisano koje su mreže pouzdanije za jednak dataset. Na kraju je pokazano da je VGG11 mreža postigla najbolje rezultate i da je u usporedbi s ostalima njeno korištenje najbolje pri klasificiranju grafičkih prikaza.
Abstract (english)
Deep artificial neural networks are today the most reliable, fastest and most effective way to solve the problem of image recognition. By using deep artificial neural network on large amount of data, the results of which can later be used in the analysis of the same (e.g. recognizing a person's face at airports). This paper describes the basic things needed to understand artificial neural networks and describes which networks are more reliable for the same dataset. In the end, it was shown that the VGG11 network achieved the best results and that, compared to the others, its use is the best for graphic classifying representation.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:514626
Study programmeTitle: Undergraduate University Study Programme
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2023-09-07 07:43:34