prikaz prve stranice dokumenta Detekcija lica korištenjem modela umjetne inteligencije
  Download
PDF 2.52 MB
undergraduate thesis
Detekcija lica korištenjem modela umjetne inteligencije
Rijeka: University of Rijeka, Faculty of Engineering, 2023. urn:nbn:hr:190:345197
Čarapina, Arian
University of Rijeka
Faculty of Engineering

Institutional repository: Repository of the University of Rijeka, Faculty of Engineering

Cite this document

Čarapina, A. (2023). Detekcija lica korištenjem modela umjetne inteligencije (Undergraduate thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:345197

Čarapina, Arian. "Detekcija lica korištenjem modela umjetne inteligencije." Undergraduate thesis, University of Rijeka, Faculty of Engineering, 2023. https://urn.nsk.hr/urn:nbn:hr:190:345197

Čarapina, Arian. "Detekcija lica korištenjem modela umjetne inteligencije." Undergraduate thesis, University of Rijeka, Faculty of Engineering, 2023. https://urn.nsk.hr/urn:nbn:hr:190:345197

Čarapina, A. (2023). 'Detekcija lica korištenjem modela umjetne inteligencije', Undergraduate thesis, University of Rijeka, Faculty of Engineering, accessed 27 August 2024, https://urn.nsk.hr/urn:nbn:hr:190:345197

Čarapina A. Detekcija lica korištenjem modela umjetne inteligencije [Undergraduate thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2023 [cited 2024 August 27] Available at: https://urn.nsk.hr/urn:nbn:hr:190:345197

A. Čarapina, "Detekcija lica korištenjem modela umjetne inteligencije", Undergraduate thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:190:345197

Metadata
TitleDetekcija lica korištenjem modela umjetne inteligencije
Title (english)Face detection using artificial intelligence model
AuthorArian Čarapina
MentorZlatan Car (mentor)
Committee memberDubravko Franković (predsjednik povjerenstva)
Committee memberZlatan Car (član povjerenstva)
GranterUniversity of Rijeka
Faculty of Engineering
Rijeka
Defense date and country2023-09-18, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Electrical Engineering
Automation and Robotics
Abstract
U ovo radu izvršena je usporedba modela za prepoznavanje lica, i to prvi model napravljen pomoću klasičnog programiranja dok je drugi model bio temeljen na umjetnoj inteligenciji te arhitekturi YOLOv5. Nakon provedene usporedbe može se zaključiti da je model koji je bio temeljen na umjetnoj inteligenciji postigao bolje rezultate pri prepoznavanju lica, no također je zahtijevao više uloženih resursa i vremena. Model kreiran klasičnim programiranjem je ostvario lošije rezultate pri prepoznavanju lica, no pri njegovoj izvedbi je utrošeno znatno manje vremena i resursa. Zaključujem da je u većini slučajeva pogodnije koristiti model temeljen na umjetnoj inteligenciji jer uloženo vrijeme i potrebni resursi opravdavaju bolje rezultate kod prepoznavanja lica. U ekstremnim slučajevima model napravljen klasičnim programiranjem može biti koristan, npr. u situacijama kada smo vremenski ograničeni ili nemamo dovoljno resursa kako bi istrenirali model
Abstract (english)
In this paper we compared two models for face recognition. First model was built using ''normal'' programing, while the second model was built using artificial inteligence based on the YOLOv5 architecture. After running the comparison, I've came to conclusion that the second model that was based on artificial inteligence performed better while recognising faces but it also consumed more time and processing power to realise. Model that was built using „normal“ programing performed worse but needed less time and processing power to create. In conclusion in most cases it is better to use the model based on artificial inteligence because invested time and computing power are justified with better results in face recognition. In extreme cases, model that was based on ''normal'' programing can be usefull, for example when we don't have enough time or we don't have enough processing power.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:190:345197
Study programmeTitle: Undergraduate University Study of Electrical Engineering
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 Attribution 4.0 International (CC BY 4.0) icon
Created on2023-09-18 08:47:09