|
|
Detection and Classification of Damage in Fingerprint Images Using Neural Nets
Vican, Peter ; Rydlo, Štěpán (referee) ; Kanich, Ondřej (advisor)
The aim of the diploma thesis is to study and propose improvement of the current convolutional neural network for the classification and detection of fingerprint disease. An improvement of the current convolutional neural network is the change of library for the algorithm of learning, detecting and classifying fingerprint damage. Other improvements are to change the convolutional neural network model and a change in the activation function. At the same time, preprocessing using the Gabor filter will be added. Another change is in the area of thresholding. Next, there will be a change in general-purpose algorithms that will simplify the work for expanding database creation, the learning process itself, the classification and detection process, and the network testing process. At the same time, this network will be expanded with a new prediction and classification. Specifically the damage caused by eczema, psoriasis, pressure and moisture. The improved convolutional neural network is implemented by PyTorch. The network detects which part of the fingerprint is damaged and draws this part into the fingerprint. At the same time, the type of disease or imprint damage is classified during detection. Synthetic fingerprints are used in network training and are supplemented by real fingerprints.
|
|
|
Local Histogram Analysis in Fingerprint Images
Glesner, Ladislav ; Drahanský, Martin (referee) ; Kanich, Ondřej (advisor)
This bachelor thesis deals with local histograms. Using these histograms, the fingerprint quality at a given location is determined. Analysis of local histograms is done using my proposed algorithms. The resulting algorithms were tested on the fingerprint database and on the damaged fingerprint database. Using these tests, a database of local histograms with a fingerprint quality rating at a specific location is created. As an extension, an algorithm for determining the quality of the entire fingerprint image is implemented.
|
|
|
Fingerprint identification algorithm
Skoupilová, Alena ; Vítek, Martin (referee) ; Kašpar, Jakub (advisor)
The main goal of this thesis is to introduce the meaning of term identification and term biometrics as a key field for fingerprint recognition. Thesis also introduces principals and types of automatic processing of fingerprint images and automatic fingerprints identification algorithms. An existing and successful methods are being described in the thesis and pre-processing of fingerprint images is being realized. Automatic fingerprint identification algorithm based on distance of minutiae from the core, core type and orientation field of the fingerprint is proposed. The proposed algorithm was tested on a database of fingerprint images and was statistically analysed.
|
|
|
Fingerprinting and Identification of TLS Connections
Hejcman, Lukáš ; Kocnová, Jitka (referee) ; Kekely, Lukáš (advisor)
TLS je dnes nejpopulárnější šifrovací protokol používaný na internetu. Jeho cílem je poskytnout vysokou úroveň zabezpečení a soukromí pro komunikaci mezi zařízeními. Představuje však výzvu z hlediska monitorování a správy sítí, protože není možné analyzovat komunikaci šifrovanou pomocí tohoto protokolu ve velkém měřítku, pomocí existujících metod založených na detailní analýze obsahu paketů. Analýza šifrované komunikace může správcům pomoci detekovat škodlivou aktivitu v jejich sítích a také jim může pomoci identifikovat potenciální bezpečnostní hrozby. V této práci představuji metodu, která nám umožňuje využít výhod dvou metod otisků TLS, JA3 a Cisco Mercury, k určení operačního systému a procesů klientů v počítačové síti. Navržená metoda je schopna dosáhnout srovnatelných nebo lepších výsledků v porovnání se stávajícím přístupem Cisco Mercury pro vybrané datové sady a zároveň poskytuje možnosti pro detailnější analýzy klasifikací než JA3. V rámci práce je dále implementován modul pro systém NEMEA, který je schopný analyzovat TLS provoz pomocí nově navrženého přístupu.
|
|
|
Generation of Skin Disease Effects into Synthetic Fingerprints from Anguli Generator
Hytychová, Tereza ; Drahanský, Martin (referee) ; Kanich, Ondřej (advisor)
The aim of this bachelor thesis is to design and implement a tool for generation of skin disease effects into synthetic fingerprints from Anguli generator. The proposed algorithms are capable of creating images with effects of warts and hyperkeratotic eczema. The OpenCV library was used for image processing. The resulting images are tested by VeriFinger and can be used for testing fingerprint recognition systems. Test results proved that both of the diseases have negative impact on fingerprint recognition. By adding effects of warts to a~fingeprint image, the image quality has decreased by up to 34 % and by adding effects of hypekeratotic eczema, the quality has decreased by up to 77 %.
|
|
|
Biometric fingerprint identification
Hodulíková, Tereza ; Smital, Lukáš (referee) ; Vítek, Martin (advisor)
This master's thesis deals with fingerprint verification. The theoretical part consist of biometry identification systems and evaluating their reliability and robustness. After that we focus on fingerprints properties needed to identification. We mention several types of fingerprint sensors, which are generaly in public use. In practical part of thesis we deal with enhancement of fingeprint image and methods of identifications. At last we created software for fingeprint identification in programming environment Matlab.
|
|
|
Analysis of Fingerprint Quality Assessment Systems
Dejmal, David ; Pernický, Radim (referee) ; Kanich, Ondřej (advisor)
The aim of this work is to improve the process of determining fingerprint quality by Fingerprint Quality Visualizer (FQV). Mutual comparison of existing programs NIST Fingerprint Image Quality 2.0 and Neurotechnology VeriFinger has proved that FQV is worse in processing of extremely small fingerprints. Therefore, the procedure which estimates the number of minutiae in fingerprint based on its real size has been designed and implemented as an improvement. The final testing has proved that the implemented method works for the selected fingerprint collection. This approach can be an alternative to complex searching and accurate minutiae counting.
|
|
|
Detection of Mobile Applications Using Traffic Profiling
Babic, Radovan ; Grégr, Matěj (referee) ; Matoušek, Petr (advisor)
This bachelor thesis deals with JA3 and JA3S methods of digital profiling of mobile applications based on TLS handshake between client and server. The thesis describes the used method of emulation of mobile devices using the Android operating system, installation of applications, generation and capture of traffic needed to create a database of profiles. Furthermore, the work describes the method that I implemented in the tool for automated creation of a database of digital profiles of applications and their subsequent classification and recognition using data obtained from internet traffic in the network.
|
|
|
Evaluation of Fingerprint Morphing Methods Compared to a Real System
Kolínek, Daniel ; Kanich, Ondřej (referee) ; Drahanský, Martin (advisor)
The aim of this work is to design methods of fingerprint morphing, subsequently to implement the proposed methods and to test their effectiveness by breaking into real verification systems made by Innovatrics and Neurotechnology, two prominent companies in biometrics. Methods for morphing were designed mainly based on the article On the Feasibility of Creating Double-Identity Fingerprints where the part of the preparation of fingerprints on the input was modified and an adjustment of the output was made so that it is able to work with fingerprint images taken under different conditions. Fingerprints created by morphing were recognized as genuine in 41.72 % of cases when compared to the default threshold. The main benefit of this work is the created application for generating fingerprints using morphing and to point out that this method is a\,threat to existing systems used for fingerprint recognition.
|
|
|
Detection and Classification of Damage in Fingerprint Images Using Neural Nets
Vican, Peter ; Drahanský, Martin (referee) ; Kanich, Ondřej (advisor)
The aim of this diploma thesis is to study and design experimental improvement of the convolutional neural network for disease detection. Another goal is to extend the classifier with a new type of detection. he new type of detection is damage fingerprint by pressure. The experimentally improved convolutional network is implemented by PyTorch. The network detects which part of the fingerprint is damaged and draws this part into the fingerprint. Synthetic fingerprints are used when training the net. Real fingerprints are added to the synthetic fingerprints.
|
guest ::
