prikaz prve stranice dokumenta Prepoznavanje lica koristeći duboke neuronske mreže
  Download
PDF 2.57 MB
master's thesis
Prepoznavanje lica koristeći duboke neuronske mreže
2022. urn:nbn:hr:122:255046
Benček, Tena
University North
University centre Varaždin
Department of Multimedia, Design and Application

Cite this document

Benček, T. (2022). Prepoznavanje lica koristeći duboke neuronske mreže (Master's thesis). Koprivnica: University North. Retrieved from https://urn.nsk.hr/urn:nbn:hr:122:255046

Benček, Tena. "Prepoznavanje lica koristeći duboke neuronske mreže." Master's thesis, University North, 2022. https://urn.nsk.hr/urn:nbn:hr:122:255046

Benček, Tena. "Prepoznavanje lica koristeći duboke neuronske mreže." Master's thesis, University North, 2022. https://urn.nsk.hr/urn:nbn:hr:122:255046

Benček, T. (2022). 'Prepoznavanje lica koristeći duboke neuronske mreže', Master's thesis, University North, accessed 21 November 2024, https://urn.nsk.hr/urn:nbn:hr:122:255046

Benček T. Prepoznavanje lica koristeći duboke neuronske mreže [Master's thesis]. Koprivnica: University North; 2022 [cited 2024 November 21] Available at: https://urn.nsk.hr/urn:nbn:hr:122:255046

T. Benček, "Prepoznavanje lica koristeći duboke neuronske mreže", Master's thesis, University North, Koprivnica, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:122:255046

Please login to the repository to save this object to your list.
Metadata
TitlePrepoznavanje lica koristeći duboke neuronske mreže
Title (english)Face recognition using deep neural networks
AuthorTena Benček
MentorEmil Dumić (mentor)
Committee memberMario Periša (predsjednik povjerenstva)
Committee memberRobert Geček (član povjerenstva)
Committee memberEmil Dumić (član povjerenstva)
GranterUniversity North
(University centre Varaždin)
(Department of Multimedia, Design and Application)
Koprivnica
Defense date and country2022-09-29, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Graphic Technology
Processes of Graphic Reproduction
Abstract
Svrha ovog rada je upoznati se s pojmom i konceptom biometrijske metode prepoznavanja lica koristeći duboke neuronske mreže. U radu je opisana biometrijska metoda prepoznavanja lica kao i njene karakteristike i povijest. Osim prepoznavanja lica pojašnjen je i pojam detekcije lica i algoritmi koji se koriste prilikom detekcije lica. Objašnjeni su stariji algoritmi za prepoznavanje lica poput Eigenface, Fisherface, histograma lokalnih binarnih uzoraka. Definiran je pojam dubokih neuronskih mreža kao i algoritmi za prepoznavanje lica koji se koriste dubokim neuronskim mrežama. Teorijski zaključi u praktičnom su dijelu podijeljeni usporedbom dva algoritma za prepoznavanje lica koji koriste duboke neuronske mreže, GoogLeNet i SqueezeNet.
Abstract (english)
The purpose of this paper is to get acquainted with the term and concept of the biometric face recognition method using deep neural networks. The paper describes the biometric face recognition method as well as its characteristics and history. In addition to face recognition, the concept of face detection and the algorithms used in face detection are also explained. Older face recognition algorithms like Eigenface, Fisherface, histogram of local binary patterns are explained. The concept of deep neural networks is defined as well as face recognition algorithms that use deep neural networks. Theoretical conclusions are divided into a practical part by comparing two face recognition algorithms that use deep neural networks, GoogLeNet and SqueezeNet.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:122:255046
Study programmeTitle: Multimedia Science
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka grafičke tehnologije (magistar/magistra inženjer/inženjerka grafičke tehnologije)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2022-11-22 09:25:05