The goal of this thesis is to extend the application for spoof effects generation into synthetic fingerprints with the possibility of generation of two new spoof effects together with annotations of generated damages. Spoof effects chosen for this thesis are areas with lower clarity and defects in spoof material. Those effects were analyzed, methods to generate those effects were designed and then implemented. According to testing, generation of two new added spoof effects led to reduction in quality of fingerprint images, as well as the value of the similarity score determined during identification. In comparison with the original solution, the quality of the fingerprints decreased more in the extended solution, the similarity score in the generation of separate spoof effect decreased overall approximately equally.

No description available.

In the domain of automatic speaker verification,  one of the challenges is to keep the malevolent people out of the system.  One way to do this is to create algorithms that are supposed to detect spoofed speech. There are several types of spoofed speech and several ways to detect them, one of which is to look at the glottal flow waveform  (GFW) of a speech signal. This waveform is often estimated using glottal inverse filtering  (GIF),  since, in order to create the ground truth  GFW, special invasive equipment is required.  To the author’s knowledge, no research has been done where the correlation of GFW accuracy and spoofed speech detection (SSD) performance is investigated. This thesis tries to find out if the aforementioned correlation exists or not.  First, the performance of different GIF methods is evaluated, then simple SSD machine learning (ML) models are trained and evaluated based on their macro average precision. The ML models use different datasets composed of parametrized GFWs estimated with the GIF methods from the previous step. Results from the previous tasks are then combined in order to spot any correlations.  The evaluations of the different methods showed that they created GFWs of varying accuracy.  The different machine learning models also showed varying performance depending on what type of dataset that was being used. However, when combining the results, no obvious correlations between GFW accuracy and SSD performance were detected.  This suggests that the overall accuracy of a GFW is not a substantial factor in the performance of machine learning-based SSD algorithms.