Národní úložiště šedé literatury Nalezeno 2 záznamů.  Hledání trvalo 0.01 vteřin. 
Algorithmic Evaluation of the Quality of Dactyloscopic Traces
Sloup, Ondřej ; Tinka, Jan (oponent) ; Drahanský, Martin (vedoucí práce)
Dactyloscopic traces are one of the critical aspects of biometric identification. They represent an element by which people can be authenticated and authorised. Nonetheless, it is necessary to evaluate if a given fingerprint is valid by the number of features it provides and decide if it is usable or useless. This analysis of features tells us how valuable the fingerprint is. We established a process that grades fingerprints based on contextual and statistical values using various enhancements and grading algorithms. These algorithms can determine if the fingerprint is good quality and whether it can be used for future processing or should be discarded. We divided fingerprints into groups based on the quality of their minutiae points, number of ridges, contrast, sinusoidal similarity and ridge thickness. We successfully evaluated fingerprints and grouped them similarly to the grouping in the NIST SD27 dataset. The algorithm's results allowed us to draw conclusions about graded fingerprints' quality and rate their usability.
Algorithmic Evaluation of the Quality of Dactyloscopic Traces
Sloup, Ondřej ; Tinka, Jan (oponent) ; Drahanský, Martin (vedoucí práce)
Dactyloscopic traces are one of the critical aspects of biometric identification. They represent an element by which people can be authenticated and authorised. Nonetheless, it is necessary to evaluate if a given fingerprint is valid by the number of features it provides and decide if it is usable or useless. This analysis of features tells us how valuable the fingerprint is. We established a process that grades fingerprints based on contextual and statistical values using various enhancements and grading algorithms. These algorithms can determine if the fingerprint is good quality and whether it can be used for future processing or should be discarded. We divided fingerprints into groups based on the quality of their minutiae points, number of ridges, contrast, sinusoidal similarity and ridge thickness. We successfully evaluated fingerprints and grouped them similarly to the grouping in the NIST SD27 dataset. The algorithm's results allowed us to draw conclusions about graded fingerprints' quality and rate their usability.

Chcete být upozorněni, pokud se objeví nové záznamy odpovídající tomuto dotazu?
Přihlásit se k odběru RSS.