|
|
Artificial neural network RCE
Maceček, Aleš ; Klusáček, Jan (referee) ; Jirsík, Václav (advisor)
This paper is focused on an artificial neural network RCE, especially describing the topology, properties and learning algorithm of the network. This paper describes program uTeachRCE developed for learning the RCE network and program RCEin3D, which is created to visualize the RCE network in 3D space. The RCE network is compared with a multilayer neural network with a learning algorithm backpropagation in the practical application of recognition letters. For a descriptions of the letters were chosen moments invariant to rotation, translation and scaling image.
|
|
| |
|
|
Face Reader
Bučko, Peter ; Juránek, Roman (referee) ; Beran, Vítězslav (advisor)
This thesis deals with computer face recognition. Methods of Components Analysis (PCA), Linear Discriminant Analysis (LDA) and Elastic Bunch Graph Matching (EBGM) are described here. Aim of this thesis is creation of a demonstration aplication for a face recognition. Moreover I test PCA and LDA methods to find out, how accurate it can be and how can be affected by changing of parameters, such as size of a database and picture count per person.
|
|
|
Estimation of Object Parameters from Images
Přibyl, Bronislav ; Hradiš, Michal (referee) ; Zemčík, Pavel (advisor)
Rapid expansion of communication technologies in last decade caused increased volume of information which is beeing generated and shared by people and organisations. It is permanently harder to identify relevant content today because of absence of tools and techniques which may support mass information management. As today's media have rather multimedial character image information is even more important. This project describes software for automatic estimation of predefined object parameters from images. A C++ implementation of this algorithm is also described.
|
|
|
Mouse Gesture Recognition
Král, Jiří ; Zuzaňák, Jiří (referee) ; Hradiš, Michal (advisor)
This project deals with Mouse gesture recognition. Proposed system models trajectories using Hidden markov model (HMM), that models gesture as an time sequence of features. In the project there are several parametrizations analyzed and compared. The best parametrization (position normalized by center of gravity and size) reached Sensitivity of recognition of 98 %.
|
|
|
Classification of digital modulation type
Balada, Radek ; Kováč,, Michal (referee) ; Povalač, Karel (advisor)
The aim of master’s thesis is a classification of digital modulation type. The interest in modulation classification has been growing for last years. It has several possible roles in both civilian and military applications such as spectrum sensing, signal confirmation, interference identification, monitoring and so on. Modulation classification is an intermediate step between signal detection and successful demodulation. Therefore the known methods are based on different statistics obtained from received signals. These statistics can be derived from continuous time signals and they hold for sampled signals.
|
|
|
Tracking and Recognition of People in Video
Šajboch, Antonín ; Hradiš, Michal (referee) ; Smrž, Pavel (advisor)
The master's thesis deals with detecting and tracking people in the video. To get optimal recognition was used convolution neural network, which extracts vector features from the enclosed frame the face. The extracted vector is further classified. Recognition process must take place in a real time and also with respect are selected optimal methods. There is a new dataset faces, which was obtained from a video record at the faculty area. Videos and dataset were used for experiments to verify the accuracy of the created system. The recognition accuracy is about 85% . The proposed system can be used, for example, to register people, counting passages or to report the occurrence of an unknown person in a building.
|
|
|
Support for education of biometric access systems
Navrátil, Petr ; Herencsár, Norbert (referee) ; Burda, Karel (advisor)
This thesis describes general function of biometric access systems and summarizes problems of their practical use. It also shows security risks of these systems. It defines basic terms, which are used in this area, describes kinds of errors and their representation. One part of this thesis deals with biometric method of fingerprints recognition. It explains fingerprints’ atomic basics, basic principles and processing of digital fingerprint image. Next part describes concrete biometric access system V-Station by Bioscrypt Inc. Besides basic description it focuses on technology of biometric sensor and algorithm, essential parts of biometric system. The thesis continues with security analysis of this concrete system. In this part I target on weak points of the system and I design possible attack on the system. In the last part of my thesis I designed laboratory exercise, which is supposed to be realized by student. It is composed it by several tasks to let students understand working with the system and attached software. At the same time, they have opportunity to think about system by themselves a make their own opinion about possibilities of the system. There are many pictures in this thesis to make term clear and to better understanding of problems of biometric security systems.
|
|
|
Recognition methods for biosignals
Juračka, Zdeněk ; Vítek, Martin (referee) ; Kolářová, Jana (advisor)
The thesis is focused on the recognition methods study used in one-dimensional signal processing. A lot of recognition methods exist, this thesis briefly describes the principle of some of them, e.g. artificial neural networks, fuzzy systems, expert systems and decision trees. Dynamic time warping (DTW) method has been chosen for signal processing available from UBMI database. DTW can be used as a non-linear signal processing method. The result of this method is to determine the similarity of two compared signals on the basis of their distance calculation. One of the reasons for choosing this method was the possibility of various length signal processing. The principle of the method as well as the calculation of the distance between two input data sequences is described in the thesis. DTW path finding method is also mentioned. The method was applied on randomly selected numbers and a set of simulated signals. The method was applied to ECG and action potential signals recorded on the isolated rabbit heart. DTW was used to evaluate shape changes of these signals in repeated phases of the experiment known as ischemia and reperfusion. Selected cardiac cycles were detected and included into different experiment phases on the basis of calculated distance results using DTW. Sensitivity was selected as an evaluative criterion of this classification method. It reached a value of 65%. DTW algorithm was further tested on the selected cardiac cycle mapping to the corresponding minute record in the selected experiment phase. It reached a sensitivity of 68.3%. The motion artifact appearance was monitored using DTW on AP signals. The method functioned more precisely on signals measured in ischemia phases. Along with the above mentioned, the thesis discusses all aspects of heart electrical manifestation activities called as ECG signals and action potentials, such as origin, propagation, recording, post-processing and measuring out.
|
|
|
Adaptation of Speaker Recognition Systems
Novotný, Ondřej ; Pešán, Jan (referee) ; Plchot, Oldřich (advisor)
In this paper, we propose techniques for adaptation of speaker recognition systems. The aim of this work is to create adaptation for Probabilistic Linear Discriminant Analysis. Special attention is given to unsupervised adaptation. Our test shows appropriate clustering techniques for speaker estimation of the identity and estimation of the number of speakers in adaptation dataset. For the test, we are using NIST and Switchboard corpora.
|
guest ::
