Sustav za prepoznavanje i pohranu značajki lica usklađen s općom uredbom o zaštiti osobnih podataka

master's thesis

• Title (english): GDPR Compliant System for Facial Features Recognition and Storage
• Author: Danijel Pavlek
• Mentor: Marin Šilić (mentor)
• Committee member: Marin Šilić (predsjednik povjerenstva)
• Committee member: Klemo Vladimir (član povjerenstva)
• Committee member: Goran Delač (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-07, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Istraživanja su pokazala da je zaštita podataka vrlo važan faktor kod korisnika,
posebice slike lica. U tu svrhu moguće je implementirati sustav koji će zaobići potrebu
za njihovim spremanjem i umjesto lica, uspored̄ivati značajke. Značajke je moguće
izračunati neuronskom mrežom. Taj pristup zadovoljava opću uredbu o zaštiti osobnih
podataka zato što iz značajki nije moguće rekonstruirati polaznu sliku. Performansa
usporedbe značajno ovisi o arhitekturi neuronske mreže i mjeri sličnosti.

Abstract (english)

Research has shown that data protection is a very important factor for users, especially facial images. For this purpose, it is possible to implement a system that will bypass the need to save them and instead of faces, compare features. The features can be calculated using a neural network. This approach satisfies the general regulation on the protection of personal data because it is not possible to reconstruct the initial image from the features. The performance of the comparison depends significantly on the neural network architecture and the degree of similarity.

• Keywords: GDPR; zaštita podataka; prepoznavanje lica; duboko učenje; transfer učenje; neuronske mreže; autoenkoderi; vađenje značajki; gradijentni spust; ADAM
• Keywords (english): GDPR; data protection; face recognition; deep learning; transfer learning; neural networks; autoencoders; feature extraction; gradient descent; ADAM
• Language: croatian
• URN:NBN: urn:nbn:hr:168:359795
• 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: 2023-01-13 10:33:28