|
|
Physical unclonable functions
Hegr, Vojtěch ; Člupek, Vlastimil (referee) ; Zeman, Václav (advisor)
The theme of the thesis is Physical Unclonable Functions (PUF). The following objectives were assigned: to provide a literature research concerning PUFs, to perform a property analysis to select appropriate type of PUF for implementation and to realize an authentication cryptosystem based on the chosen PUF. Based on the research, the cryptosystem was designed based on ring oscillator PUF. The proposed cryptosystem is tested in several scenarios with the maximal rate of successful authentication of 81%. The cryptosystem also allows to be used for device identification. Furthermore, the results were discussed and suitable improvements of design was proposed. Besides the cryptosystem itself, the thesis also introduced a unique comparison of existing types of PUFs.
|
|
|
Classifiaction algorithms for face-based identification systems
Hegr, Vojtěch ; Křupka, Aleš (referee) ; Malach, Tobiáš (advisor)
The thesis deals with the research of classification algorithms for face-based identification. The aim is to implement algorithms into an existing system for face recognition and the evaluation of the impect of individual classifiers. According to the survey of face recognition methods the following classifiers were chosen for implementation: K - Nearest Neighbours (K-NN), Support Vector Machines (SVM) and the Neural Networks. These classification algorithms were implemented in C++ (Microsoft Visual Studio 2010) using the open source library OpenCV. Furthermore, the IFaVID database and the methodology used to test the implemented algorithms were introduced.
|
|
|
Physical unclonable functions
Hegr, Vojtěch ; Člupek, Vlastimil (referee) ; Zeman, Václav (advisor)
The theme of the thesis is Physical Unclonable Functions (PUF). The following objectives were assigned: to provide a literature research concerning PUFs, to perform a property analysis to select appropriate type of PUF for implementation and to realize an authentication cryptosystem based on the chosen PUF. Based on the research, the cryptosystem was designed based on ring oscillator PUF. The proposed cryptosystem is tested in several scenarios with the maximal rate of successful authentication of 81%. The cryptosystem also allows to be used for device identification. Furthermore, the results were discussed and suitable improvements of design was proposed. Besides the cryptosystem itself, the thesis also introduced a unique comparison of existing types of PUFs.
|
|
|
Classifiaction algorithms for face-based identification systems
Hegr, Vojtěch ; Křupka, Aleš (referee) ; Malach, Tobiáš (advisor)
The thesis deals with the research of classification algorithms for face-based identification. The aim is to implement algorithms into an existing system for face recognition and the evaluation of the impect of individual classifiers. According to the survey of face recognition methods the following classifiers were chosen for implementation: K - Nearest Neighbours (K-NN), Support Vector Machines (SVM) and the Neural Networks. These classification algorithms were implemented in C++ (Microsoft Visual Studio 2010) using the open source library OpenCV. Furthermore, the IFaVID database and the methodology used to test the implemented algorithms were introduced.
|
guest ::
RSS feed.