|
|
Visual Anomaly Detection in Industrial Production
Hrabica, Jan ; Richter, Miloslav (referee) ; Horák, Karel (advisor)
This thesis deals with the problem of unary classifiers for anomaly detection in industrial production. It starts with a discussion of classification as a general problem, classification methods and some of their evaluations, and then discusses the main categories of architectures used. Practical part describes the process of scene creation for the acquisitions of a datesed. Acquired dataset is then used for teaching a classifier, on which is then performer a number of experiments to determine its performance.
|
|
|
Thermovision of photovoltaic modules automatic analysis
Repko, Ilia ; Křivík, Petr (referee) ; Vaněk, Jiří (advisor)
This work deals with the automatic evaluation of thermographic images of photovoltaic modules. In theoretical part of work described main principles of sun's battery work and methods for detection defects, that affecting the quality work, including method thermography, which is based on principle of contactless measuring the surface temperature the observed object. Practical part dedicated to creation of algorithms for detection defects, result is a source code for the program MATLAB.
|
|
|
Cards Recognition Using Android
Klusoň, Martin ; Polok, Lukáš (referee) ; Pavelková, Alena (advisor)
This work deals with design of an application for the mobile operating system Android. Application recognize playing cards and their values from image from camera device. Application helps to count points in game Rummy. Recognition is solved by a combination of three cascaded classifiers. Solutions based on keypoint detection and OCR proved useless. The application detects values of cards (excluding jokers), not their colors.
|
|
|
Coevolution of Image Filters and Noise Detectors
Komjáthy, Gergely ; Zachariášová, Marcela (referee) ; Drahošová, Michaela (advisor)
This thesis deals with image filter design using coevolutionary algorithms. It contains a description of evolutionary algorithms, focusing on genetic programming, cartesian genetic programming and coevolution, the reader can learn about image filters too. The next chapters contain the design of image filters and noise detectors using cooperative coevolution, and the implementation and testing of the proposed filter. In the last chapter the proposed filter is compared to other filters created using evolutionary algorithms but without coevolution.
|
|
|
Filtering methods for NMR measurements
Zvěřina, Lukáš ; Rajmic, Pavel (referee) ; Gescheidtová, Eva (advisor)
The subject of this thesis is the principle of modern filtering techniques of signals acquired by nuclear magnetic resonance technique. In the NMR images a disturbing element is almost always present, especially noise, which causes useful signal and image degradation. The noise is a random signal, related to the errors of measurement and evaluation. The noise brings no information about the behaviour of the signal and it is unwanted signal component. The bachelor thesis is therefore focused mainly on the removal of the interfering parts of the signals. It exploits the fact that the nowadays widely expanding wavelet transform is closely connected with the banks of the digital filters. The subsequent section deals with experimental filtering of signals by implementation the wavelet transform in Matlab.
|
|
|
Image sensor signal data processing
Růžička, Jakub ; Macháň, Ladislav (referee) ; Žák, Jaromír (advisor)
This diploma thesis deals with an image capturing by a CMOS image sensor and controlling of graphical LCD displays using specialized integrated circuits. A theoretical research on the topic and design of the system designed for ease of processing, transmitting and still images displaying based on this research is described in this work. The output of the work is complete the device realized.
|
|
|
Colearning in Coevolutionary Algorithms
Wiglasz, Michal ; Dobai, Roland (referee) ; Drahošová, Michaela (advisor)
Cartesian genetic programming (CGP) is a form of genetic programming where candidate programs are represented in the form of directed acyclic graphs. It was shown that CGP can be accelerated using coevolution with a population of fitness predictors which are used to estimate the quality of candidate solutions. The major disadvantage of the coevolutionary approach is the necessity of performing many time-consuming experiments to determine the best size of the fitness predictor for the particular task. This project introduces a new fitness predictor representation with phenotype plasticity, based on the principles of colearning in evolutionary algorithms. Phenotype plasticity allows to derive various phenotypes from the same genotype. This allows to adapt the size of the predictors to the current state of the evolution and difficulty of the solved problem. The proposed algorithm was implemented in the C language and optimized using SSE2 and AVX2 vector instructions. The experimental results show that the resulting image filters are comparable with standard CGP in terms of filtering quality. The average speedup is 8.6 compared to standard CGP. The speed is comparable to standard coevolutionary CGP but it is not necessary to experimentally determine the best size of the fitness predictor while applying coevolution to a new, unknown task.
|
|
|
Coevolution of Image Filters and Noise Detectors
Komjáthy, Gergely ; Zachariášová, Marcela (referee) ; Drahošová, Michaela (advisor)
This thesis deals with image filter design using coevolutionary algorithms. It contains a description of evolutionary algorithms, focusing on genetic programming, cartesian genetic programming and coevolution, the reader can learn about image filters too. The next chapters contain the design of image filters and noise detectors using cooperative coevolution, and the implementation and testing of the proposed filter. In the last chapter the proposed filter is compared to other filters created using evolutionary algorithms but without coevolution.
|
|
|
Thermovision of photovoltaic modules automatic analysis
Repko, Ilia ; Křivík, Petr (referee) ; Vaněk, Jiří (advisor)
This work deals with the automatic evaluation of thermographic images of photovoltaic modules. In theoretical part of work described main principles of sun's battery work and methods for detection defects, that affecting the quality work, including method thermography, which is based on principle of contactless measuring the surface temperature the observed object. Practical part dedicated to creation of algorithms for detection defects, result is a source code for the program MATLAB.
|
|
|
Filtering methods for NMR measurements
Zvěřina, Lukáš ; Rajmic, Pavel (referee) ; Gescheidtová, Eva (advisor)
The subject of this thesis is the principle of modern filtering techniques of signals acquired by nuclear magnetic resonance technique. In the NMR images a disturbing element is almost always present, especially noise, which causes useful signal and image degradation. The noise is a random signal, related to the errors of measurement and evaluation. The noise brings no information about the behaviour of the signal and it is unwanted signal component. The bachelor thesis is therefore focused mainly on the removal of the interfering parts of the signals. It exploits the fact that the nowadays widely expanding wavelet transform is closely connected with the banks of the digital filters. The subsequent section deals with experimental filtering of signals by implementation the wavelet transform in Matlab.
|
guest ::
