|
|
Fingerprint Processing
Pšenák, Patrik ; Krajsa, Ondřej (referee) ; Říha, Kamil (advisor)
My master's thesis deals with the different techniques used in fingerprints processing for identifying fingerprints. Using the software tool Visual C++ and functions of OpenCV library I programmed a separate application, that is able to select from a database of fingerprints the most consistent with a comparative fingerprint images, even when they are mutually shifted in the direction of axes X and Y. The next step in my program is to gather the edges of the fingerprint image. Those obtained using Canny edge detector. Furthermore, getting the contours of the image edges. To determine, whether the contours are the same, just compare some characteristic points of contours. Next I use a histogram function to determine the number of points for approximation of contours and evaluating compliance fingerprints. Since the processing of the input fingerprint image (or rather the approximation of the contour points) remains in the picture as black (background) and red (the approximation of the contour points), this means, that zero and the last element of the histogram represent the number of black and red points. Comparison is in percentage and is obtained by subtracting the approximated points of contours image from the original fingerprint image of approximated contour points of matched fingerprints. It determined, what percentage of red points have disappeared, so as to match two fingerprint images. If on the resulting figure is not left neither a red point, that corresponds to 100% of the fingerprints Compliance.
|
|
|
Methodology of Fingerprint Image Quality Measurement
Oravec, Tomáš ; Drahanský, Martin (referee) ; Kanich, Ondřej (advisor)
This thesis deals with the problem of methodology of fingerprint image quality measurement. The first task was to analyze already existing software used for fingerprint quality measurement called NFIQ (NIST Fingerprint Image Quality), evaluate its performance and identify weaknesses. In order to eliminate discovered NFIQ weaknesses, different fingerprint quality estimation methodology was introduced, and its results were compared to other methodologies.
|
|
|
Recognition of Fine Skin Movements on a Fingertip
Dragula, Peter ; Orság, Filip (referee) ; Drahanský, Martin (advisor)
Heutzutage beeinflusst die Biometrie mehr und mehr unsere Leben. Diese Technologie soll uns Sicherheit und auch Bequemlichkeit erschaffen. Biometrische Systeme ersetzen jeden Tag ältere Sicherheitssysteme und die Firmen versprechen sich mehr Leistung zu bekommen. Aber trotzdem kann man über viele Bereiche der Biometrie sagen, dass sie noch zurückgeblieben sind. In meiner Arbeit analysiere ich den Zustand der ganzen biometrischen Industrie, ich lerne die neuesten Technologien kennen. Die Mängel dieser Industrie sind noch deutlich und es müssen noch viele Innovationen durchgesetzt werden. Ich widme mich meistens der Sicherheit der biometrischen Systeme, konkret orientiere ich mich auf die Fingerabdruckstechnologie. Nach der Analyse der neuesten Angriffe und Sicherheitsvorgänge, werte ich die Technik der Erkennung der feinen Hautbewegungen der Fingerspitzen aus.
|
|
|
Biometric Liveness Detection for the Fingerprint Recognition Technology
Brabec, Lukáš ; Váňa, Jan (referee) ; Drahanský, Martin (advisor)
This work focuses on liveness detection for the fingerprint recognition technology. The first part of this thesis describes biometrics, biometric systems, liveness detection and the method for liveness detection is proposed, which is based on spectroscopic characteristics of human skin. The second part describes and summarizes performed experiments. In the end, the results are discussed and further improvements are proposed.
|
|
|
Fingerprint Classification
Kostiha, Martin ; Orság, Filip (referee) ; Drahanský, Martin (advisor)
Automatic identification based on fingerprints requires the input fingerprint to be matched with a large number of fingerprints stored in a database. Fingerprint classification provides an important indexing mechanism in fingerprint databases that reduces the search time and computational complexity. This thesis is dealing with Galton-Henry's classification system. The classification method is based on orientation field and detection singularities using Poinaceré index.
|
|
|
Analysis of Fingerprint Spoofs Created from Mold Done by Etching Technique
Tilgner, Jan ; Sakin, Martin (referee) ; Kanich, Ondřej (advisor)
This work aims to analyse fingerprint spoofs from mold created by etching. Mold will be created using the technique used to create printed circuit board. After that spoof will be cast using liquid latex and then scanned. Created spoofs will then be compared to their original image. Algorithm to evaluate these spoofs is designed and implemented. The algorithm works by comparing pairs of minutiae from each fingerprint if they are similar. This alghoritm will be tested on database of fingerprint spoofs and the results will be compared to existing software results. Spoofs created by this technique had poor quality and minutiae did not match the original fingerprint.
|
|
|
Revocable Fingerprint Created by Morphing
Tilgner, Jan ; Semerád, Lukáš (referee) ; Kanich, Ondřej (advisor)
This thesis is concerned with the development of an application that will be able to ge- nerate a morphed fingerprint by combining an input fingerprint with a suitable synthetic fingerprint from a database so that the resulting morph matches revocable biometrics. The issue of fingerprint morphing is still a little explored area and in combination with revoca- ble biometry, this paper is unique. The described functionality will be added to an existing application to create a morphed fingerprint. In this work, the theoretical knowledge requi- red to implement this application has been described step by step, and an algorithm for generating revocable morphs based on splitting the original fingerprint into segments and then creating morphs from these segments has been proposed. Subsequently, this algorithm was implemented and tested using the VeriFinger tool. The algorithm for splitting the print into 6 and 10 segments achieved the best results. For 6 segments, the algorithm achieved an average similarity score to the original fingerprint of 52.1, where always approximately 60% of the generated morphs were suitable for matching. For 10 segments, the score was 54.64 with a similar proportion of suitable morphs. When comparing morphs against each other, the algorithm achieved a score of 10.5 with 6 segments and 16.28 with 10 segments. The proportion of positive comparisons was below 10% for 6 segments and around 10 to 15% for 10 segments.
|
|
|
Animal Identification Based on Biometric Information
Plička, Maxim ; Šátek, Václav (referee) ; Rydlo, Štěpán (advisor)
This bachelor thesis is focused on obtaining information from a photograph of animal's muzzle pattern that will be used to identify the individual. The main goal is to propose and implement an application that can extract this information from the input photo and then output it, or find the photo in the database that most closely matches the input photo. The main purpose of the testing was to determine the accuracy of extracting this information. The proposed approach achieved 82.71% accuracy with a database size of 171 photos. The photographs belonged to deer and does.
|
|
|
Laboratory exercise of the biometric access control system
Volf, Jakub ; Dobiáš, Patrik (referee) ; Burda, Karel (advisor)
This thesis deals with the topic of biometric access control. The theoretical part of the thesis first describes electronic access control in general, followed by access control based on human biometric traits. Legislation and the development of biometric control representation in the market are briefly mentioned in this work. Based on the provided components, a panel is designed and manufactured in the practical part. The individual components are implemented in the panel and connected according to the manual. This assembly thus forms a functional system for biometric access control, which will be used as one of the laboratory tasks in educational classes. There is a written method, based on the laboratory task, specifically designed for student and a documentation for the teacher on how to operate this system.
|
|
|
Synthetic Fingerprints Generator with Dactyloscopic Minutiae
Kodaj, Radoslav ; Sakin, Martin (referee) ; Kanich, Ondřej (advisor)
The goal of this thesis is to improve algorithm for synthetic fingerprint generation using dactyloscopic minutiae. The focus will be on the analysis of minutiae and on the creating of algorithm that will generate enhanced fingerprints. The improvement consists in using larger scale of minutiae . This work also includes basic knowledge about fingerprints, their sensing and recognition. The theory also deals with the study of generation methods from which the improved generator is also developed. The improved generator is created according to the design. The results of the improvement of fingerprint generation by the new algorithm are also summarized.
|
guest ::
