|
|
New technologies for biometric recognition based on hand characteristics
Dvořák, Michal ; Jadlovský, Ján (referee) ; Marcialis, Gian Luca (referee) ; Drahanský, Martin (advisor)
Biometrie nám umožňuje identifikovat či verifikovat osoby na základě jejich fyzických vlastností. Přestože identifikace samotná je velmi rychlá, extrakce zvolené biometrie v reálném světě je netriviální problém. Pro snímání většího množství lidí, například na letišti, potřebujeme dosáhnout snímání a rozpoznání v co nejkratším čase, ideálně za chůze uživatele. Tato disertační práce se zabývá vývojem bezdotykového a tedy hygienického biometrického systému, který je schopen provést extrakci identifikačních charakteristik ruky a následně rozpoznat uživatele za běhu. Spolu s tím práce obsahuje další systémy a algoritmy potřebné pro řešení tohoto komplexního problému. Práce prezentuje současný stav výzkumu a vývoje v oblasti biometrické identifikace na základě vybraných charakteristik, se zaměřením na identifikaci pomocí geometrie ruky a otisků prstů. Dále se pak v2nuje technologickým principům využitých pro sběr těchto biometrických charakteristik. Dle disertačních cílů, formulovaných na základě rešerše, se praktická část této práce zabývá vývojem biometrických systémů pro použití k identifikaci velkého množství lidí za běhu, pro které většina současných biometrických systémů založených na charakteristikách ruky nejsou vhodné. Dále pak se práce zabývá souvisejícími problémy, zejména pak detekcí prezentačního útoku a biometrickou multimodalitou.
|
|
|
Contactless User Authentification Using Leap Motion Sensor
Lukáč, Jakub ; Beran, Vítězslav (referee) ; Najman, Pavel (advisor)
Contactless authentication of users has grown in popularity as a new technology. Recent findings in the field of computer vision and its applications have contributed to the emergence of new devices such as Leap Motion controller. This device is capable of precise recognition of hand positions and simple gestures identification. This paper presents an application of data gathered from controller's interface and using them for user identification. Proposed solution uses hand geometry to evaluate the recognition process where this accessible and inexpensive device can be used. Therefore, the user can easily benefit from this extra feature coming with the new device. To conclude, the results show overall accuracy over 99 % on a relatively small dataset.
|
|
|
Reconstruction of Human Hand Surface for the Purpose of Biometric Recognition of Persons
Svoboda, Jan ; Drahanský, Martin (referee) ; Dluhoš, Ondřej (advisor)
The goal of this work is to create a device and design an algorithm for the recostruction of human hand surface for the purpose of biometric recognition of persons. First of all existing approaches to human hand surface reconstruction are introduced. Subsequently the theoretical base of the methods used in the solution is shown. Also, the device con- struction is presented in more detail to the reader. After that the reconstruction algorithm implementation is described. In the end, experiments and results are presented.
|
|
|
Support for Fingerprint Authentication
Bartoň, Jaroslav ; Beran, Vítězslav (referee) ; Mlích, Jozef (advisor)
The goal of the thesis is the finger-print authentication support within the Linux operating system and the K Desktop Environment (KDE). Theoretical part of the thesis firstly explains main IT security terms and ways to proof the identity. Secondly it describes biometric systems and types of processed biometric characteristics. Lastly the features of finger-prints, their markants as well as types of scanners used in scanning the finger-prints and ways to analyze the scanned material have been elaborated. Practical solution part of the thesis develops and establishes finger-print management application and plugin for KDM graphics login manager.
|
|
|
Biometric System Performance Testing - Hand Geometry Technology
Hrnčiřík, Matej ; Orság, Filip (referee) ; Lodrová, Dana (advisor)
This thesis describes difficulties of testing one of many biometric technologies - hand geometry technology. Several procedures were designed to test this technology. The whole testing process was performed on HandKey II device. One of the objectives was to determine whether the device can be fooled using artificial hands. Next objective was to design and perform tests aimed at identification and verification. Results are processed and evaluated from several aspects.
|
|
|
Hand Extraction from a Photo with Different Backgrounds
Kováčik, Timotej ; Kanich, Ondřej (referee) ; Sakin, Martin (advisor)
This thesis focuses on extraction of human hand from photographs with different backgrounds. The goal is to design and implement an algorithm capable of locating human hand in the image and identifying its parts. It analyses the methods of biometric identification and verification, methods used for extracting objects from an image. The outcome of this thesis is a design and implementation of an algorithm that is able to extract human hand from a photo and identify its parts.
|
|
|
Hand and Finger Detection in the Video Sequences
Šulek, Jakub ; Procházka, Boris (referee) ; Dluhoš, Ondřej (advisor)
The thesis deals with problems concerning detection of human hand and fingers in the videosequences, especially navigation and determination of correct distribution of fingers. There is an opening presentation of existing biometrics, description of biometric system and hand anatomy. After are given the methods of hand geometry recognition and functional example description. Consequently there is a proposal of a new solution. Program uses open source OpenCV library based on hand's significant points detection. The next part of the thesis is dedicated to navigation, detection of known states and description of order determining mechanism.
|
|
|
Hand Extraction from a Photo with Different Backgrounds
Kováčik, Timotej ; Kanich, Ondřej (referee) ; Sakin, Martin (advisor)
This thesis focuses on extraction of human hand from photographs with different backgrounds. The goal is to design and implement an algorithm capable of locating human hand in the image and identifying its parts. It analyses the methods of biometric identification and verification, methods used for extracting objects from an image. The outcome of this thesis is a design and implementation of an algorithm that is able to extract human hand from a photo and identify its parts.
|
|
|
Contactless User Authentification Using Leap Motion Sensor
Lukáč, Jakub ; Beran, Vítězslav (referee) ; Najman, Pavel (advisor)
Contactless authentication of users has grown in popularity as a new technology. Recent findings in the field of computer vision and its applications have contributed to the emergence of new devices such as Leap Motion controller. This device is capable of precise recognition of hand positions and simple gestures identification. This paper presents an application of data gathered from controller's interface and using them for user identification. Proposed solution uses hand geometry to evaluate the recognition process where this accessible and inexpensive device can be used. Therefore, the user can easily benefit from this extra feature coming with the new device. To conclude, the results show overall accuracy over 99 % on a relatively small dataset.
|
|
|
Biometric System Performance Testing - Hand Geometry Technology
Hrnčiřík, Matej ; Orság, Filip (referee) ; Lodrová, Dana (advisor)
This thesis describes difficulties of testing one of many biometric technologies - hand geometry technology. Several procedures were designed to test this technology. The whole testing process was performed on HandKey II device. One of the objectives was to determine whether the device can be fooled using artificial hands. Next objective was to design and perform tests aimed at identification and verification. Results are processed and evaluated from several aspects.
|
guest ::
