Ocenjevanje kvalitete prstnega odtisa na biometrični napravi

diplomsko delo

Haris Kupinić (Author), Jure Žabkar (Mentor)

Abstract

Identifikacija prstnega odtisa predstavlja eno izmed trenutno najbolj uporabljanih metod verifikacije za pristop do številnih sistemov. Zajem slik je lahko precej kompleksen problem, saj je odvisen od različnih faktorjev, ki močno vplivajo na kvaliteto delovanja senzorja. V diplomski nalogi smo raziskali to področje z vidika umetne inteligence. Predstavljeni pristopi bodo uporabljeni kot varovalka pred uporabo slabih zajemov – izvedli bodo realno analizo slike ter bodo zmožni končnemu uporabniku podati oceno kvalitete njegovega prstnega odtisa. Učna množica, pridobljena s strani ekspertov, predstavlja vhod v model. Izhod je binarna ocena, ki ocenjuje sliko kot “slabo” ali “dobro”.

Keywords

prstni odtis;kvaliteta slik;univerzitetni študij;diplomske naloge;

Data

Language:	Slovenian
Year of publishing:	2022
Typology:	2.11 - Undergraduate Thesis
Organization:	UL FRI - Faculty of Computer and Information Science
Publisher:	[H. Kupinić]
UDC:	004.8:57.087.1(043.2)
COBISS:	135349507
Views:	31
Downloads:	8
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Fingerprint image quality assessment on a biometric device
Secondary abstract:	Fingerprint identification represents one of the most popular methods of verification for accessing many systems. Capturing images is pretty complex problem, as it depends on many different factors that highly impact the functionality of the sensor. In this thesis, we have researched this field from the perspective of AI. Used methods will be implemented as safety system as they prevent bad captures – they will analyse the image and give some quality grade of the image to the final user. Used dataset, obtained from the field experts, is used as the input for the model. Output is a binary value, that values an image as a “good” or “bad”.
Secondary keywords:	machine learning;fingerprint;biometry;artificial intelligence;image quality;computer science;diploma;Strojno učenje;Biometrija;Umetna inteligenca;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:	36 str.
ID:	17509548