|
| |
|
|
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.
|
|
|
The Use of SVM in Environment of Financial Markets
Štechr, Vladislav ; Prochocká, Kristína (referee) ; Budík, Jan (advisor)
This thesis deals with use of regression or classification based on support vector machines from machine learning field. SVMs predict values that are used for decisions of automatic trading system. Regression and classification are evaluated for their usability for decision making. Strategy is being then optimized, tested and evaluated on foreign exchange market Forex historic data set. Results are promising. Strategy could be used in combination with other strategy that would confirm decisions for entering and exiting trades.
|
|
|
Object Classification Using Radar
Přívara, Jan ; Zemčík, Pavel (referee) ; Maršík, Lukáš (advisor)
The aim of this bachelor's thesis is to design and implement classification system using radar, specifically vehicle classification system. The first part describes both radar principles and radar signal processing methods. A brief introduction to machine learning is provided, with emphasis on Support Vector Machines classification model. Feature extraction methods from radar signal are discussed as well. The next part describes concept and implementation of system for vehicle classification. In the end, the implemented classification system is evaluated and the possible continuation of this work is stated.
|
|
|
Detection and Classification of Military Targets in a Videosignal
Košík, Michal ; Orság, Filip (referee) ; Drahanský, Martin (advisor)
The aim of this thesis is to design and implement algorithms for detection and classification of distant targets. The reader will become familiar with algorithms for detection of a movement, namely image difeerentiation and an algorithm based on a Bayes classifier. In the following two possible ways of classification, one using support vector machines and the second one utilizing a set of linear classifiers, will be introduced. At the end of this thesis results of the algorithms will be described and evaluated.
|
|
| |
|
|
Automatic Photography Categorization
Veľas, Martin ; Beran, Vítězslav (referee) ; Španěl, Michal (advisor)
This thesis deals with content based automatic photo categorization. The aim of the work is to create an application, which is would be able to achieve sufficient precision and computation speed of categorization. Basic solution involves detection of interesting points, extraction of feature vectors, creation of visual codebook by clustering, using k-means algorithm and representing visual codebook by k-dimensional tree. Photography is represented by bag of words - histogram of presence of visual words in a particular photo. Support vector machines (SVM) was used in role of classifier. Afterwards the basic solution is enhanced by dividing picture into cells, which are processed separately, computing color correlograms for advanced image description, extraction of feature vectors in opponent color space and soft assignment of visual words to extracted feature vectors. The end of this thesis concerns to experiments of of above mentioned techniques and evaluation of the results of image categorization on their usage.
|
|
|
Document Topic Classification
Oravec, Jakub ; Černocký, Jan (referee) ; Smrž, Pavel (advisor)
This bachelor's thesis deals with automatic document topic classification and provides a brief introduction to this area of research. The first part contains summary of basic techniques used in natural language processing with emphasis on text classification methods. The next part describes concept and implementation of system for automatic document topic classification. The last part contains information about testing of created system including composition of testing set and standard metrics description.
|
|
|
Face Recognition
Keršner, Martin ; Mlích, Jozef (referee) ; Juránek, Roman (advisor)
The thesis deals with Face Recognition. The aim was to study the various methods of feature extraction and determine their influence on the success of recognition. The methods of feature extraction include the Local Binary Pattern, Histogram Of Oriented Gradients and Gabor Filter. Face recognition of image similarity will be described. Support Vectore Machines was used in the experiments. Experimentally determined parameters of the most successful methods were used in the system for simple Face Recognition.
|
|
|
Tracking Judge Including Gestures in Agility
Palata, Petr ; Přibyl, Bronislav (referee) ; Herout, Adam (advisor)
This thesis focuses on tracking an Agility judge including his gestures. The beginning is dedicated to a brief introduction into Agility. After that, a conceptual system is presented and its parts are then described in the individual chapters. The thesis evaluates availa- ble open-source human trackers and integrates them into the system. Posture and hand recognition are done using two SVM classifiers trained with Bag of Words descriptors.
|
guest ::
