|
|
Automatic vocal-oriented recognition of human emotions
Houdek, Miroslav ; Přinosil, Jiří (referee) ; Atassi, Hicham (advisor)
This master thesis concerns with emotional states and gender recognition on the basis of speech signal analysis. We used various prosodic and cepstral features for the description of the speech signal. In the text we describe non-invasive methods for glottal pulses estimation. The described features of speech were implemented in MATLAB. For their classification we used the GMM classifier, which uses the Gaussian probability distribution for modeling a feature space. Furthermore, we constructed a system for recognition of emotional states of the speaker and a system for gender recognition from speech. We tested the success of created systems with several features on speech signal segments of various lengths and compared the results. In the last part we tested the influence of speaker and gender on the success of emotional states recognition.
|
|
|
Camera surveillance system
Lazarević, Veljko ; Přinosil, Jiří (referee) ; Koton, Jaroslav (advisor)
The bachelor thesis is focused on the introduction and design of a camera system. The theoretical part briefly deals with the description of individual components and basic parameters of the camera system, especially the personal protection. Security systems today rely heavily on cameras. Cameras can be useful in identifying potential threats and protecting people and property. It is important to take precautionary measures to protect yourself and your property. This bachelor thesis deals with various camera systems, namely analog, hybrid and currently digital. The practical part is about the design, installation and maintenance of a digital camera system.
|
|
|
Vehicle detection in images
Pálka, Zbyněk ; Přinosil, Jiří (referee) ; Krajsa, Ondřej (advisor)
This thesis dissert on traffic monitoring. There are couple of different methods of background extraction and four methods vehicle detection described here. Furthermore there is one method that describes vehicle counting. All of these methods was realized in Matlab where was created graphical user interface. One whole chapter is dedicated to process of practical realization. All methods are compared by set of testing videos. These videos are resulting in statistics which diagnoses about efficiency of single one method.
|
|
|
Watermarking of digital data
Kupka, Jan ; Přinosil, Jiří (referee) ; Číka, Petr (advisor)
The main aim of this project is to implement two different types of the watermarking algorithm in frequency (transforamtion) domain. Because of the huge amount of the watermarking algorithms is this thesis dedicated to the watermarking methods in the frequency domain. These methods use kind of transformation implemented on the original data, the second step is modification of transformation coeficients. This project is dedicated to the methods which use discrete wavelet transformation. Nowdays the most popular transformation, which meets the best efforts. The aim of every method is to embeed the watermark into the original data so precisly, that none observer can recognize any change between the original and watermarked data. On the contrary, watermarked picture should be as resistant to the attacks as possible. By the term of attack, we understand all the ways, that disable watermark extraction. The watermark method robustness will be tested with the use of Checkmark program.
|
|
|
Masked face recognition
Kašpar, Jan ; Kříž, Petr (referee) ; Přinosil, Jiří (advisor)
This bachelor thesis focuses on the recognition of people with covered faces. The work describes four algorithms InsightFace, FaceNet, OpenFace, and face recognition. From these algorithms, the most suitable for recognizing people with a covered face is selected. Two databases of persons are created, and two models for the recognition of persons are trained; one is for the recognition of persons with a covered face and the other for non-covered persons. ROC curves are created for these models to determine the accuracy of the models. The created program is used to recognize people or to add them to the database created by SQLite.
|
|
|
Image based flower recognition
Jedlička, František ; Kříž, Petr (referee) ; Přinosil, Jiří (advisor)
This paper is focus on flowers recognition in an image and class classification. Theoretical part is focus on problematics of deep convolutional neural networks. The practical part if focuse on created flowers database, with which it is further worked on. The database conteins it total 13000 plant pictures of 26 spicies as cornflower, violet, gerbera, cha- momile, cornflower, liverwort, hawkweed, clover, carnation, lily of the valley, marguerite daisy, pansy, poppy, marigold, daffodil, dandelion, teasel, forget-me-not, rose, anemone, daisy, sunflower, snowdrop, ragwort, tulip and celandine. Next is in the paper described used neural network model Inception v3 for class classification. The resulting accuracy has been achieved 92%.
|
|
|
Non-linear character of optical environment
Žáček, Martin ; Míča, Ivan (referee) ; Přinosil, Jiří (advisor)
This paper describes theoretical and application options of nonlinear effects in optical medium. Optical medium means fiber optics, because the fiber is the most employed optical medium at these days. Basic statements of this work are theoretical information with mathematical and physical expressions. These expressions defines nonlinear medium and effects which are founded here. These effects are split to second and third orders. Nonlinear effects of second orders are Second-harmonic Generation, Three-wave Mixing process. Nonlinear effects third orders are Third-harmonic Generation, Self-phase Modulation, Cross-phase Modulation, Four-wave Mixing and Degenerative Four-wave Mixing process. These effects are extended by scattering effects – Brillouin’s and Raman‘s Scattering. The next point discuss about optical communication system DWDM. DWDM uses dense wavelength multiplexing. Nonlinear effects have a few negative influences on these systems. There are requests for high bandwidth and communication speed. FWM and XPM limit these requests. They can invoke cross-talks. We support theoretical information with application examples and simulations at the end of this work. We use OptSim v.4.0 program. We are simulate FWM and XPM effect in depend on chromatical dispersion and power.
|
|
|
Tracking the movement of objects in the video signal
Šidó, Balázs ; Kříž, Petr (referee) ; Přinosil, Jiří (advisor)
Tato diplomova prace se zameruje na sledovani pohybu vice objektu. Prace popisuje dve implementace filtru, ktere jsou v podstate zalozeny na principu Kalmanova filtru. Obe implementace jsou zalozeny na principu sledovani vice objektu, na zaklade znalosti pozic vsech objektu v kazdem snimku. Prvni implementace je smisena verze Globalniho a Standardniho filtru nejblizsich sousedu. Druha implementace je postavena na pravde- podobnostnim pristupu k procesu sdruzeni. Posledni kapitola poskytuje srovnani mezi temito filtry a Zakladnim filtrem. Algoritmy byly realizovany v jave.
|
|
|
Enhancement of bio-medical image signals
Gregor, Michal ; Šmirg, Ondřej (referee) ; Přinosil, Jiří (advisor)
When scanning biomedical images by magnetic resonance or ultrasound, unwanted elements in the form of noise are entered to the image. With help of various methods it is possible the noise from the image partially remove. There are many methods for noise reduction and every one works on a different principle. As a result of this the results of these methods are different and is necessary for them to be objectively assessed. There is use for the adjustment of the images wavelet transformation and some treshold techniques in the work. The quality of the resulting pictures is tested by the methods for objective quallity tests. Testing was done in the MATLAB program environment on the pictures from magnetic resonance and pictures from ultrasound.
|
|
|
Image classification using deep learning
Hřebíček, Zdeněk ; Přinosil, Jiří (referee) ; Mašek, Jan (advisor)
This thesis deals with image object detection and its classification into classes. Classification is provided by models of framework for deep learning BVLC/Caffe. Object detection is provided by AlpacaDB/selectivesearch and belltailjp/selective_search_py algorithms. One of results of this thesis is modification and usage of deep convolutional neural network AlexNet in BVLC/Caffe framework. This model was trained with precision 51,75% for classification into 1 000 classes. Then it was modified and trained for classification into 20 classes with precision 75.50%. Contribution of this thesis is implementation of graphical interface for object detction and their classification into classes, which is implemented as aplication based on web server in Python language. Aplication integrates object detection algorithms mentioned abowe with classification with help of BVLC/Caffe. Resulting aplication can be used for both object detection (and classification) and for fast verification of any classification model of BVLC/Caffe. This aplication was published on server GitHub under license Apache 2.0 so it can be further implemented and used.
|
guest ::
