|
|
Heart beat classification
Potočňák, Tomáš ; Kozumplík, Jiří (referee) ; Ronzhina, Marina (advisor)
The aim of this work was to develop the method for classification of ECG beats into two classes, namely ischemic and non-ischemic beats. Heart beats (P-QRS-T cycles) selected from animals orthogonal ECGs were preprocessed and used as the input signals. Spectral features vectors (values of cross spectral coherency), principal component and HRV parameters were derived from the beats. The beats were classified using feedforward multilayer neural network designed in Matlab. Classification performance reached the value approx. from 87,2 to 100%. Presented results can be suitable in future studies aimed at automatic classification of ECG.
|
|
|
Real-time Facial Feature Tracking
Peloušek, Jan ; Mekyska, Jiří (referee) ; Přinosil, Jiří (advisor)
This thesis considers the problematic of the object recognition in a digital picture, particularly about the human face recognition and its components. There are described the basics of the computer vision, the object detector Viola-Jones, its computer realization with help of the OpenCV libraries and the test results. This thesis also describes the accurate system of the facial features detection per the algorithm of the Active Shape Models and also related mechanism of the classifier training, including the software implementation.
|
|
|
Development of algorithms for digital real time image processing on a DSP Processor
Knapo, Peter ; Sajdl, Ondřej (referee) ; Belgium, Jurgen Baert (MSc), KHBO (advisor)
Rozpoznávanie tvárí je komplexný proces, ktorého hlavným ciežom je rozpoznanie žudskej tváre v obrázku alebo vo video sekvencii. Najčastejšími aplikáciami sú sledovacie a identifikačné systémy. Taktiež je rozpoznávanie tvárí dôležité vo výskume počítačového videnia a umelej inteligencií. Systémy rozpoznávania tvárí sú často založené na analýze obrazu alebo na neurónových sieťach. Táto práca sa zaoberá implementáciou algoritmu založeného na takzvaných „Eigenfaces“ tvárach. „Eigenfaces“ tváre sú výsledkom Analýzy hlavných komponent (Principal Component Analysis - PCA), ktorá extrahuje najdôležitejšie tvárové črty z originálneho obrázku. Táto metóda je založená na riešení lineárnej maticovej rovnice, kde zo známej kovariančnej matice sa počítajú takzvané „eigenvalues“ a „eigenvectors“, v preklade vlastné hodnoty a vlastné vektory. Tvár, ktorá má byť rozpoznaná, sa premietne do takzvaného „eigenspace“ (priestor vlastných hodnôt). Vlastné rozpoznanie je na základe porovnania takýchto tvárí s existujúcou databázou tvárí, ktorá je premietnutá do rovnakého „eigenspace“. Pred procesom rozpoznávania tvárí, musí byť tvár lokalizovaná v obrázku a upravená (normalizácia, kompenzácia svetelných podmienok a odstránenie šumu). Existuje mnoho algoritmov na lokalizáciu tváre, ale v tejto práci je použitý algoritmus lokalizácie tváre na základe farby žudskej pokožky, ktorý je rýchly a postačujúci pre túto aplikáciu. Algoritmy rozpoznávania tváre a lokalizácie tváre sú implementované do DSP procesoru Blackfin ADSP-BF561 od Analog Devices.
|
|
|
Possibilities of using multi - dimensional statistical analyses methods when evaluating reliability of distribution networks
Geschwinder, Lukáš ; Skala, Petr (referee) ; Blažek, Vladimír (advisor)
The aim of this study is evaluation of using multi-dimensional statistical analyses methods as a tool for simulations of reliability of distribution network. Prefered methods are a cluster analysis (CLU) and a principal component analysis (PCA). CLU is used for a division of objects on the basis of their signs and a calculation of the distance between objects into groups whose characteristics should be similar. The readout can reveal a secret structure in data. PCA is used for a location of a structure in signs of multi-dimensional matrix data. Signs present separate quantities describing the given object. PCA uses a dissolution of a primary matrix data to structural and noise matrix data. It concerns the transformation of primary matrix data into new grid system of principal components. New conversion data are called a score. Principal components generating orthogonal system of new position. Distribution network from the aspect of reliability can be characterized by a number of new statistical quantities. Reliability indicators might be: interruption numbers, interruption time. Integral reliability indicators might be: system average interruption frequency index (SAIFI) and system average interruption duration index (SAIDI). In conclusion, there is a comparison of performed SAIFI simulation according to negatively binomial division and provided values from a distribution company. It is performed a test at description of sign dependences and outlet divisions.
|
|
|
Image data processing using principal component analysis (PCA)
Solnický, Jan ; Archalous, Tomáš (referee) ; Rychtárik, Milan (advisor)
This project deals with using of principal component analysis (PCA) in image processing and its aim is introduce mathematical apparatus of principal component analysis and possibility of its using in image processing. Project contains instructions how to compress images with using PCA and also how to convert colour image to grayscale intensity image. There are shown how to use PCA to denoising operation in wavelet spectrum. Project includes results of that operations and their evaluation.
|
|
|
Human body detection in a video scene
Šmirg, Ondřej ; Číka, Petr (referee) ; Kohoutek, Michal (advisor)
The project consists of two distinct levels i.e. separation level and diagnostic level. At the separation level, statistical models of gaussians and color are separately used to classify each pixel as belonging to backgroung or foreground. Adopted method is mixture of gaussians.A mixture of gaussians model is suitable here because the results of the picture tests will not depend on the lens opening, but rather on the colors in the backgroung. A mixture of gaussians model for return data seems reasonable. The achieved results the used method on the real sequences are presented in the thesis. Diagnostic level is identified human body on the scene. Adopted method is ASM(Active Shape Models) with PCA(Principal Component Analysis). ASM are statistical models of the shape of human bodies which iteratively deform to fit to an example of the object in a new image.
|
|
|
Overview of methods for person identification using image processing
Palacka, Martin ; Březina, Lukáš (referee) ; Krejsa, Jiří (advisor)
This thesis deals with an overview of methods for person identification using image processing. The beginning of thesis is dedicated to the theoretical study of the skin segmentation method, its algorithm and different color spaces, which are used for identification by this method. The next algorithm is a method called boosted cascade of simple features, while focusing on description of this method, an OpenCV library, computing algorithm, image interpretation by integral image and speed of computation which is reached. The next chapter describes the PCA method, the principles of working, a description of the mathematical model, a study of gender recognition, the results and troubleshooting. The last described methods are fusion of facial strips and pixel patern based texture feature. At the end of this thesis there is the tested application of person identification and gender recognition and the results of the success of methods.
|
|
|
From single feature to settlement pattern, landscape and society: a methodological approach to castellological research
Novák, David
Fortified manors are in the scope of interest from the 19th century and at present, we have solid and complex knowledge base, which can be evaluated to obtain interesting results. Most of the published papers dealing with fortified manors have undergone basic chronological and typological analysis without further interest in their spatial attributes or their relation to the hinterland. This fact and underestimation of quantitative analysis and statistics may be explained in the context of the culture-history paradigm, still prevailing in Czech archaeology. Alternatively, perhaps, it is just a result of the methodological inability of many archaeologists to deal with large data sets. As a response to this situation, the author attempts to look at fortified manors in another way - through statistical methods and using GIS. Paper is aimed to present methodology used in case study of selected region in western part of Central Bohemia as a sample.
|
|
| |
|
|
Special Issue on the 18th International Conference on Artificial Neural Networks
Húsek, Dušan ; Neruda, Roman ; Koutník, J.
Special Issue on the 18th International Conference on Artificial Neural Networks. Neural Network World. Vol. 19, No. 5 (2009). The issue contains papers prepared specially for this issue by authors of some best evaluated papers presented on ICANGA 2008 conference. Covered are mainly following topics: Mathematical Theory of Neurocomputing, Computational Neuroscience, Connectionist Cognitive Science, Neuroinformatics, Image Processing, Signal and Time Series Processing, Reinforcement Learning, Binary Factor Analysis, Principal Component Analysis, Self-organization, Neural Network Hardware.
|
guest ::
