diplomsko delo
Blaž Pelko (Author), Žiga Emeršič (Mentor)

Abstract

V zadnjem desetletju so dosežki v umetni inteligenci prinesli nove možnosti za biometrično avtentikacijo posameznikov, s čimer se je pojavila potreba po uporabi teh rešitev na mobilnih napravah. V diplomski nalogi se osredotočamo na problematiko prepoznavanja identitete na podlagi uhljev s pomočjo mobilne naprave. Za rešitev tega izziva smo razvili aplikacijo, ki temelji na dveh glavnih segmentih: razvoju modelov za zaznavanje (algoritem YOLO) in prepoznavanje uhljev (MobileNetV3) s pomočjo strojnega učenja in implementacije razvitih modelov v razvojnem orodju Android studio. Rezultati kažejo, da je s pomočjo sodobne tehnologije mogoče zanesljivo in uspešno prepoznati uhlje na mobilnih napravah, kar odpira nove poti za nadaljnje raziskave na tem področju.

Keywords

biometrija uhljev;prepoznavanje identitete;univerzitetni študij;diplomske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.11 - Undergraduate Thesis
Organization: UL FRI - Faculty of Computer and Information Science
Publisher: [B. Pelko]
UDC: 004.93:57.087.1:004.9(043.2)
COBISS: 162275843 Link will open in a new window
Views: 64
Downloads: 22
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Ear biometrics on mobile devices
Secondary abstract: In the last decade, advancements in artificial intelligence have opened new possibilities for bio-metric authentication of individuals, thereby creating a need for the application of these solutions on mobile devices. In this thesis, we focus on the issue of identifying an individual based on the features of the ear using a mobile device. To address this challenge, we have developed an application based on two main segments: the development of models for detection (the YOLO algorithm) and ear recognition (MobileNetV3) through machine learning, and the implementation of these developed models in the Android studio development tool. Results demonstrate that, with the aid of current technology, it's possible to reliably and successfully recognize ears on mobile devices, opening new paths for further research in this area.
Secondary keywords: ear bio-metrics;recognition;mobile applications;computer science;diploma;Biometrična identifikacija;Računalniški vid;Mobilne aplikacije;Računalništvo;Univerzitetna in visokošolska dela;
Type (COBISS): Bachelor thesis/paper
Study programme: 1000468
Embargo end date (OpenAIRE): 1970-01-01
Thesis comment: Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages: 52 str.
ID: 19833929