Detekcija i raspoznavanje lica u slikama

undergraduate thesis

• Title (english): Face Detection and Recognition in Images
• Author: Tomislav Lovrenčić
• Mentor: Zoran Kalafatić (mentor)
• Committee member: Zoran Kalafatić (predsjednik povjerenstva)
• Committee member: Matej Grcić (član povjerenstva)
• Committee member: Franjo Matković (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-07, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu prikazan je jedan od mogućih načina pristupa prepoznavanju lica koji se može primijeniti u sustavima identifikacije, provjeri dokumenata, sigurnosnom nadzoru pristupa itd. Opisan je originalni algoritam i implementacija prepoznavanja lica Adama Geitgeya. Utvrđeno je da predloženi algoritam prepoznavanja lica zadovoljavajuće funkcionira u nepovoljnim uvjetima osvjetljenja, varijacijama kontrasta te raznim pozama lica. Postigli smo točnost prepoznavanja od 100% za predstavljene pristupe u kontroliranom okruženju. Uz prave i kvalitetne slike određenih pojedinaca, na primjer ljudi unutar jedne tvrtke, potpuno je sigurno primijeniti softver za prepoznavanje lica kao sigurnosnu mjeru.

Abstract (english)

In this work one approach to face recognition has been presented, which may be applied in identification systems, document control and access control. An original algorithm and implementation of Adam Geitgey face recognition was described. The proposed face recognition algorithm was found to perform satisfactorily in adverse conditions of light exposure, contrast variations, and diffrent face poses. We achieved the recognition accuracy of 100% for the presented approaches in a controlled environment like the one described in paper. With the right training photos of certain individuals , for example in a company, it is perfectly safe to implement face recognition software for security measures.

• Keywords: prepoznavanje lica; HOG deskriptor; strojno učenje
• Keywords (english): face recognition; HOG descriptor; machine learning
• Language: croatian
• URN:NBN: urn:nbn:hr:168:362257
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-14 21:00:47