Sigurnosna vrata s antropomorfnim svojstvom prepoznavanja

master's thesis

• Title (english): Security door with an anthropomorphic recognition feature
• Author: Marin Herak
• Mentor: Mladen Crneković (mentor)
• Granter: University of Zagreb; Faculty of Mechanical Engineering and Naval Architecture; Zagreb
• Defense date and country: 2023-12-07, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mechanical Engineering

Abstract

U sklopu diplomskog rada prikazana je važnost implementacije tehnologija prepoznavanja lica, otiska prsta i glasovne komunikacije u kontekstu otvaranja sigurnosnih vrata. Navedene su već postojeće metode i tehnike navedenih tehnologija kao i već postojeći proizvodi. Jedan od tih je i NEC koji je globalni lider u području biometrijske autentifikacije, s šest originalnih tehnologija biometrijske autentifikacije. HOG algoritam koji se koristi za prepoznavanje lica u ovom diplomskom radu je detaljnije opisan jer je važan dio ovog rada. Najvažnija komponenta ovog rada je, u današnje vrijeme, jako popularno računalo Raspberry Pi koje spojeno sa navedenim komponentama čini funkcionalnu cjelinu. Nakon programiranja, teorija je potvrđena eksperimentom i kako sam sklop radi. On radi na način da za otvaranje vrata potrebno ispravno lice i otisak prsta inače ulaz nije dopušten i sve je to popraćeno glasovnom komunikacijom prema korisniku. Ovim radom je stvoren temelj za daljnji razvoj sličnih sustava i pristupa unutar područja kontrole pristupa i sigurnosti prostora.

Abstract (english)

The importance of implementing facial recognition, fingerprint, and voice communication technologies in the context of opening secure doors is presented within the framework of the master's thesis. Existing methods and techniques of these technologies, as well as already available products, are discussed. One such product is NEC, a global leader in biometric authentication, with six original biometric authentication technologies. The HOG algorithm used for facial recognition in this thesis is detailed as it is a crucial part of the work. The most significant component of this thesis is the widely popular Raspberry Pi computer, which, when connected with the mentioned components, forms a functional unit. After programming, the theory is confirmed through experimentation, demonstrating the functioning of the system. It operates by requiring the correct face and fingerprint for door access; otherwise, entry is not permitted, accompanied by voice communication with the user. This work establishes a foundation for further development of similar systems and approaches in the field of access control and space security.

• Keywords: prepoznavanje lica; prepoznavanje otiska prsta; glasovna komunikacija; sigurnosna vrata; NEC; HOG algoritam; Raspberry Pi
• Keywords (english): facial recognition; fingerprint recognition; voice communication; security doors; NEC; HOG algorithm; Raspberry Pi
• Language: croatian
• URN:NBN: urn:nbn:hr:235:644985
• Study programme: Title: Mechanical Engineering; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka strojarstva (magistar/magistra inženjer/inženjerka strojarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2023-11-29 18:20:03