prikaz prve stranice dokumenta Sustav za kontrolu pristupa temeljen na prepoznavanju lica
  Download
PDF 2.95 MB
master's thesis
Sustav za kontrolu pristupa temeljen na prepoznavanju lica
Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2020. urn:nbn:hr:200:225710
Jagodić, Valentino
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Computer Engineering and Automation
Chair of Automation and Robotics

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

Cite this document

Jagodić, V. (2020). Sustav za kontrolu pristupa temeljen na prepoznavanju lica (Master's 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:200:225710

Jagodić, Valentino. "Sustav za kontrolu pristupa temeljen na prepoznavanju lica." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2020. https://urn.nsk.hr/urn:nbn:hr:200:225710

Jagodić, Valentino. "Sustav za kontrolu pristupa temeljen na prepoznavanju lica." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2020. https://urn.nsk.hr/urn:nbn:hr:200:225710

Jagodić, V. (2020). 'Sustav za kontrolu pristupa temeljen na prepoznavanju lica', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 27 November 2024, https://urn.nsk.hr/urn:nbn:hr:200:225710

Jagodić V. Sustav za kontrolu pristupa temeljen na prepoznavanju lica [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2020 [cited 2024 November 27] Available at: https://urn.nsk.hr/urn:nbn:hr:200:225710

V. Jagodić, "Sustav za kontrolu pristupa temeljen na prepoznavanju lica", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:200:225710

Metadata
TitleSustav za kontrolu pristupa temeljen na prepoznavanju lica
Title (english)Access control system based on facial recognition
AuthorValentino Jagodić
MentorEmmanuel Karlo Nyarko (mentor)
Committee memberEmmanuel Karlo Nyarko (predsjednik povjerenstva)
Committee memberRatko Grbić (član povjerenstva)
Committee memberPetra Đurović (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Computer Engineering and Automation)
(Chair of Automation and Robotics)
Osijek
Defense date and country2020-10-09, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
Potreba za većim stupnjem sigurnosti u modernom dobu dovela je do razvoja naprednih sustava poput onog za prepoznavanje lica. Povijest sustava za prepoznavanje lica prati se od 60-ih godina 20. stoljeća, od ručnog unosa do kompleksnih modela koji se nalaze čak i na mobilnim uređajima. Zadatak ovog diplomskog rada bio je istražiti i izraditi sustav za prepoznavanje lica koristeći neuronske mreže. Kako bi neuronska mreža bila uspješno istrenirana, jedan od problema bio je način predobrade podataka. Dimenzionalnost podataka smanjena je korištenjem histograma orijentiranih gradijenata. Sustav je programiran u programskom jeziku Python zbog jednostavnosti rada s neuronskim mrežama. Također, izvršena je usporedba postojećih modela kako bi se došlo do najboljeg modela. Koristeći neuronske mreže istrenirane na prethodno obrađenim podatcima, sustav uspješno pronalazi i prepoznaje osobu na fotografiji.
Abstract (english)
Need for increased security in modern age lead to development of advanced systems such as one for facial recognition. The history of face recognition systems dates back to the 1960s, from manual input to complex models found even on mobile devices. The task of this thesis was to research and develop a system for facial recognition using neural networks. In order for the neural network to be successfully trained, one of the problems was the way to pre-process data. Data dimensionality was reduced using histograms of oriented gradients. System was developed in programming language Python for its simplicity of working with neural networks. Furthermore, a comparison of existing models was conducted in order to discover what the best model is. Using neural networks trained on previously processed data, the system successfully finds and recognizes the person in the given photo.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:225710
Study programmeTitle: Graduate University Study Programme in Computer Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2020-12-07 10:48:40