Thesis Details
Algorithmic Evaluation of the Quality of Dactyloscopic Traces
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.
image processing, fingerprints, quality analysis, dactyloscopic traces, sinusoidal similarity, ridge thickness, contrast, minutiae points, fingerprint enhancement, fingerprint segmentation, contrast difference, SD27, number of papillary ridges, LatFigGra
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT), člen
Holík Lukáš, doc. Mgr., Ph.D. (DITS FIT BUT), člen
Martínek Tomáš, doc. Ing., Ph.D. (DCSY FIT BUT), člen
Matoušek Petr, doc. Ing., Ph.D., M.A. (DIFS FIT BUT), člen
@bachelorsthesis{FITBT25028, author = "Ond\v{r}ej Sloup", type = "Bachelor's thesis", title = "Algorithmic Evaluation of the Quality of Dactyloscopic Traces", school = "Brno University of Technology, Faculty of Information Technology", year = 2022, location = "Brno, CZ", language = "english", url = "https://www.fit.vut.cz/study/thesis/25028/" }