izpis_h1_title_alt

Izboljšava modela za deidentifikacijo z uporabo generativnih nasprotniških mrež
ID Sušin, Nejc (Author), ID Peer, Peter (Mentor) More about this mentor... This link opens in a new window, ID Štruc, Vitomir (Co-mentor)

.pdfPDF - Presentation file, Download (24,64 MB)
MD5: E59662CA65C4BC6AF8D214C5587C5804

Abstract
Sodobna družba se vse bolj zaveda pomembnosti varovanja osebnih podatkov in zasebnosti. Prikrivanje identitet posameznikov na fotografijah ali video posnetkih je zato pomembno opravilo. Sodoben pristop k reševanju tega problema je generiranje nadomestnih obrazov, s katerimi zakrijemo izvirne. Algoritem imenovan $k$-Same-Net uporabi generativno nevronsko mrežo, ki sintetizira nadomestne obraze brez podobnosti resničnim osebam. Pristop je uspešen, vendar so generirani obrazi neraznoliki, slike pa niso povsem ostre. Naš cilj je izboljšava stabilnosti generativnega postopka in kvalitete rezultatov z uporabo najnovejših metod s področja generativnih modelov, natančneje z generativnimi nasprotniškimi mrežami. Preizkusili smo številne različne arhitekture in postopke učenja. Zaradi težavnega učenja generativnih nasprotniških mrež, ki je razvidno tudi iz našega dela, nismo prišli do zadovoljivih rezultatov. Nekatere implementacije uspešno posnemajo človeški obraz, izraz na obrazu in celo identiteto. Ni pa nam uspelo odkriti kombinacije parametrov, ki bi se naučila na podlagi več vhodnih identitet generirati prepričljiv nov obraz.

Language:Slovenian
Keywords:deidentifikacija, generativne nasprotniške mreže, generiranje obrazov
Work type:Master's thesis/paper
Organization:FRI - Faculty of Computer and Information Science
Year:2019
PID:20.500.12556/RUL-113562 This link opens in a new window
COBISS.SI-ID:1538495939 This link opens in a new window
Publication date in RUL:21.01.2020
Views:1022
Downloads:251
Metadata:XML RDF-CHPDL DC-XML DC-RDF
:
Copy citation
Share:Bookmark and Share

Secondary language

Language:English
Title:Improving a deidentification model using generative adversarial networks
Abstract:
In a privacy-concerned society it is a common challenge to protect the identities of people appearing in a photo or video. A modern approach is to generate surrogate faces to replace the originals. An algorithm called $k$-Same-Net uses generative neural networks to synthesize faces without any visual resemblance to real people. While highly successful, it suffers from low variety and blurriness of the generated faces. Our goal was to improve the quality and stability of this process by applying the latest methods in the field of generative neural networks, namely generative adversarial networks. We compare the quality of faces generated by several different implementations. Due to the difficulties of training generative networks, which are evident from our work, we were unable to achieve satisfactory results. Some of the methods we present are successful in imitating human faces, emotions and even identities. However, we were unsuccessful in finding a set of parameters that would result in convincing new identities based on multiple existing faces.

Keywords:deidentification, generative adversarial networks, generating faces

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Back