|
|
Statistical analysis of ROC curves
Kutálek, David ; Bednář, Josef (referee) ; Michálek, Jaroslav (advisor)
The ROC (Receiver Operating Characteristic) curve is a projection of two different cumulative distribution functions F0 and F1. On axis are values 1-F0(c) and 1-F1(c). The c-parameter is a real number. This curve is useful to check quality of discriminant rule which classify an object to one of two classes. The criterion is a size of an area under the curve. To solve real problems we use point and interval estimation of ROC curves and statistical hypothesis tests about ROC curves.
|
|
|
Impact of color models on performance of convolutional neural networks
Šimunský, Martin ; Doležel, Petr (referee) ; Škrabánek, Pavel (advisor)
Current knowledge about impact of colour models on performance of convolutional neural network is investigated in the first part of this thesis. The experiment based on obtained knowledge is conducted in the second part. Six colour models HSV, CIE 1931 XYZ, CIE 1976 L*a*b*, YIQ a YCbCr and deep convolutional neural network ResNet-101 are used. RGB colour model achieved the highest classification accuracy, whereas HSV color model has the lowest accuracy in this experiment.
|
|
|
Segmentation Methods in Biomedical Image Processing
Mikulka, Jan ; Přibil, Jiří (referee) ; Dostál, Otto (referee) ; Gescheidtová, Eva (advisor)
The PhD thesis deals with modern methods of image processing, especially image segmentation, classification and evaluation of parameters. It is focused primarily on processing medical images of soft tissues obtained by magnetic resonance tomography (MR) and microscopic images of tissues. It is easy to describe edges of the sought objects using of segmented images. The edges found can be useful for further processing of monitored object such as calculating the perimeter, surface and volume evaluation or even three-dimensional shape reconstruction. The proposed solutions can be used for the classification of healthy/unhealthy tissues in MR or other imaging. Application examples of the proposed segmentation methods are shown in this thesis. Research in the area of image segmentation is focused on methods based on solving partial differential equations. This is a modern method for image processing, often called the active contour method. It is of great advantage in the segmentation of real images degraded by noise with fuzzy edges and transitions between objects. The results of the thesis are methods proposed for automatic image segmentation and classification.
|
|
|
Object clasification based on its topology change using image processing
Zbavitel, Tomáš ; Věchet, Stanislav (referee) ; Krejsa, Jiří (advisor)
The aim of the present work is to select a suitable object classification method for the recognition of one-handed finger alphabet characters. For this purpose, a sufficiently robust dataset has been created and is included in this work. The creation of the dataset is necessary for training the convolutional neural network. Further more, a suitable topology for data classification was found. The whole work is implemented using Python and the open-source library Keras was used.
|
|
| |
|
| |
|
|
Automatic Photography Categorization
Gajová, Veronika ; Hradiš, Michal (referee) ; Španěl, Michal (advisor)
Purpose of this thesis is to design and implement a tool for automatic categorization of photos. The proposed tool is based on the Bag of Words classification method and it is realized as a plug-in for the XnView image viewer. The plug-in is able to classify a selected group of photos into predefined image categories. Subsequent notation of image categories is written directly into IPTC metadata of the picture as a keyword.
|
|
|
Event detection in camera records
Smolnikov, Mikhail ; Sikora, Pavel (referee) ; Horváth, Tomáš (advisor)
This bachelor thesis focuses on the problem of detection and classification of moving objects in video sequences. The thesis describes the basic algorithms and methods of image data processing, including an introduction to the use of neural networks. The practical part shows the internal logic of a desktop application that allows users to evaluate their own video sequences for the occurrence of movements. The resulting application speeds up the process of video analysis on a selected device many times over.
|
|
|
Object clasification based on its topology change using image processing
Zbavitel, Tomáš ; Věchet, Stanislav (referee) ; Krejsa, Jiří (advisor)
The aim of the present work is to select a suitable object classification method for the recognition of one-handed finger alphabet characters. For this purpose, a sufficiently robust dataset has been created and is included in this work. The creation of the dataset is necessary for training the convolutional neural network. Further more, a suitable topology for data classification was found. The whole work is implemented using Python and the open-source library Keras was used.
|
|
|
Impact of color models on performance of convolutional neural networks
Šimunský, Martin ; Doležel, Petr (referee) ; Škrabánek, Pavel (advisor)
Current knowledge about impact of colour models on performance of convolutional neural network is investigated in the first part of this thesis. The experiment based on obtained knowledge is conducted in the second part. Six colour models HSV, CIE 1931 XYZ, CIE 1976 L*a*b*, YIQ a YCbCr and deep convolutional neural network ResNet-101 are used. RGB colour model achieved the highest classification accuracy, whereas HSV color model has the lowest accuracy in this experiment.
|
guest ::
