Prepoznavanje lica korisnika za primjene u pametnom uredu

undergraduate thesis

• Title (english): User Face Recognition for Smart Office Applications
• Author: Karlo Ježić
• Mentor: Ivana Podnar Žarko (mentor)
• Committee member: Ivana Podnar Žarko (predsjednik povjerenstva)
• Committee member: Dario Pevec (član povjerenstva)
• Committee member: Petar Krivić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-03, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu prikazane su tehnologije i algoritmi koji su danas primjenjivi za rješavanje problema prepoznavanja lica te odabrane tehnologije i implementacija sustava koji omogućuje osobi ulazak u pametni ured na temelju prepoznavanja njegovog lica iz struje videa. Sustav koristeći metode strojnog i dubokog učenje detektira lice, prepoznaje njegove ključne značajke te na temelju njih izrađuje 128-dimenzionalno polje koje uspoređuje s prije izrađenim poljima „poznatih lica“ iz baze podataka, te ovisno o toj usporedbi određuje ima li osoba ovlasti ući u pametni ured ili ne.

Abstract (english)

This paper presents technologies and algorithms that are today applicable to solve the problem of face recognition, and selected technologies and implementation of a system that allows a person to enter a smart office by recognizing his face. Using machine and deep learning, the system detects the face, recognizes its key features and creates a 128-dimensional field called embedding. The system then compares previously created embeddings of “known persons” from the database and depending on its similarity determines whether a person has the authority to enter a smart office or not.

• Keywords: računalni vid; detekcija lica; prepoznavanje lica; duboko učenje; strojno učenje; Python; Java; JavaScript; HTML; CSS; Spring Boot; Raspberry Pi; ZeroMQ; Thymeleaf
• Keywords (english): computer vision; face detection; face recognition; deep learning; machine learning; Python; Java; JavaScript; HTML; CSS; Spring Boot; Raspberry Pi; ZeroMQ; Thymeleaf
• Language: croatian
• URN:NBN: urn:nbn:hr:168:187394
• 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 09:00:23