Detekcija i raspoznavanje lica u slikama

master's thesis

• Title (english): Face detection and recognition in images
• Author: Katarina Golub
• Mentor: Zoran Kalafatić (mentor)
• Committee member: Zoran Kalafatić (predsjednik povjerenstva)
• Committee member: Tomislav Hrkać (član povjerenstva)
• Committee member: Vladimir Čeperić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-02-29, Croatia

Abstract

Detekcija lica, koja služi kao početni korak u sustavima raspoznavanja lica, ima veliki značaj jer pronalazi široku primjenu u raznim područjima kao što su biometrija, analiza izraza lica, raspoznavanje orijentira lica, praćenje lica i uljepšavanje lica. U ovom radu prikazan je rad tradicionalnih metoda raspoznavanja lica te popularnih metoda dubokog učenja. Neki značajni modeli dubokog učenja koji se koriste za raspoznavanje lica uključuju FaceNet, DeepFace i VGGFace. U sklopu zadatka prikazan je rad alata DeepFace problemu identifikacije osoba na manjem skupu podataka, kao što je album slika. Također, prikazane su primjene sustava za raspoznavanje lica u stvarnim aplikacijama.

Abstract (english)

Face detection, which serves as the initial step in face recognition systems, is of great importance because it finds wide application in various fields such as biometrics, facial expression analysis, facial landmark recognition, face tracking and facial beautification. This paper presents the work of traditional facial recognition methods and popular deep learning methods. Some notable deep learning models used for face recognition include FaceNet, DeepFace, and VGGFace. As part of the task, the work of the DeepFace tool on the problem of person identification on a smaller set of data, such as a picture album, is presented. Also, applications of facial recognition systems in real applications are presented.

• Keywords: Detekcija lica; Raspoznavanje lica; Tradicionalne metode; DeepFace; Duboko učenje
• Keywords (english): Face detection; Face recognition; Traditional methods; Deepface; Deep learning
• Language: croatian
• URN:NBN: urn:nbn:hr:168:914813
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2024-03-28 07:46:25