|
|
Research in Fingerprint Damage Simulations
Kanich, Ondřej ; Matyáš, Václav (oponent) ; Champod, Christophe (oponent) ; Drahanský, Martin (vedoucí práce)
The goal of this research is to develop methods for fingerprint damage simulations. In the first part of this thesis the emphasis is placed on a summary of the current knowledge of synthetic fingerprint generation and the damage to these fingerprints. Moreover, general information about fingerprints, fingerprint recognition, and phenomena that damage fingerprints including skin diseases are stated herein. This thesis contains the design and implementation of the SyFDaS application for generation and modular damaging of fingerprints. The next part is a description of methods for damage by swipe mode, narrow sensor, damaged sensor, pressure and moisture, skin distortion, warts, atopic eczema, and psoriasis. Several other types of damage, including fingerprint spoofs, are analysed. Overall, there are 43 basic damages which were visually verified. Due to damage combinations, there are 1,171 types of damage and 348,300 fingerprint images generated, which were evaluated by four different quality measurement methods.
|
|
|
Synthetic Fingerprint Generation Using GAN
Dvořák, Jiří ; Drahanský, Martin (oponent) ; Kanich, Ondřej (vedoucí práce)
This thesis is focused on the generation of synthetic fingerprints using a model based on the principle of generative adversarial networks. The work summarizes the basic theoretical information about biometrics with emphasis on fingerprints. It also describes the principle of one of the popular synthetic fingerprint generators called SFinGe. The model based on a deep convolutional generative adversarial network is discussed together with several methods that improved its performance. The results were evaluated by computing the Fréchet Inception Distance between the generated and real fingerprints. The generated dataset of 100 samples was also evaluated by NFIQ 2.0 which proved that the proposed model is able to generate fingerprints with almost the same quality of the training samples.
|
|
|
Synthetic Fingerprint Generation Using GAN
Dvořák, Jiří ; Drahanský, Martin (oponent) ; Kanich, Ondřej (vedoucí práce)
This thesis is focused on the generation of synthetic fingerprints using a model based on the principle of generative adversarial networks. The work summarizes the basic theoretical information about biometrics with emphasis on fingerprints. It also describes the principle of one of the popular synthetic fingerprint generators called SFinGe. The model based on a deep convolutional generative adversarial network is discussed together with several methods that improved its performance. The results were evaluated by computing the Fréchet Inception Distance between the generated and real fingerprints. The generated dataset of 100 samples was also evaluated by NFIQ 2.0 which proved that the proposed model is able to generate fingerprints with almost the same quality of the training samples.
|
|
|
Research in Fingerprint Damage Simulations
Kanich, Ondřej ; Matyáš, Václav (oponent) ; Champod, Christophe (oponent) ; Drahanský, Martin (vedoucí práce)
The goal of this research is to develop methods for fingerprint damage simulations. In the first part of this thesis the emphasis is placed on a summary of the current knowledge of synthetic fingerprint generation and the damage to these fingerprints. Moreover, general information about fingerprints, fingerprint recognition, and phenomena that damage fingerprints including skin diseases are stated herein. This thesis contains the design and implementation of the SyFDaS application for generation and modular damaging of fingerprints. The next part is a description of methods for damage by swipe mode, narrow sensor, damaged sensor, pressure and moisture, skin distortion, warts, atopic eczema, and psoriasis. Several other types of damage, including fingerprint spoofs, are analysed. Overall, there are 43 basic damages which were visually verified. Due to damage combinations, there are 1,171 types of damage and 348,300 fingerprint images generated, which were evaluated by four different quality measurement methods.
|
host ::
RSS.