|
|
Supporting Board Game Nemesis on Android Mobile Phone
Štěpánek, Miroslav ; Švec, Tomáš (referee) ; Smrž, Pavel (advisor)
The aim of this thesis is to create a mobile application for the board game Nemesis designed for the Android system, which will allow the user to find out information about the game components during the game. The solution consists of two main parts the first is a model created with the help of the Tensorflow library, which is responsible for the detection of these components. The second is the application itself, which receives results from the model and displays the resulting information to the user. This makes the game easier for the user and helps to speed it up. The resulting system can be modified so that the application can be used for other games.
|
|
|
Land cover classfication using artificial neural networks
Oubrechtová, Veronika ; Štych, Přemysl (advisor) ; Kupková, Lucie (referee)
Land cover classification using artificial neural networks Abstract This Diploma thesis deals with automatic classification of the satellite high spatial resolution image in the field of land cover. The first half of the work contains the theoretical information about remote sensing and classification methods. The biggest attention is given to the artificial neural networks. In practical part of Diploma thesis are these methods used for the classification of SPOT satellite image. Keywords: remote sensing, image classification, artificial neural networks, SPOT
|
|
|
Active learning for Bayesian neural networks in image classification
Belák, Michal ; Šabata, Tomáš (advisor) ; Vomlelová, Marta (referee)
In the past few years, complex neural networks have achieved state of the art results in image classification. However, training these models requires large amounts of labelled data. Whereas unlabelled images are often readily available in large quantities, obtaining l abels takes considerable human effort. Active learning reduces the required labelling effort by selecting the most informative instances to label. The most popular active learning query strategy framework, uncertainty sampling, uses uncertainty estimates of the model being trained to select instances for labelling. However, modern classification neural networks often do not provide good uncertainty estimates. Baye sian neural networks model uncertainties over model parameters, which can be used to obtain uncertainties over model predictions. Exact Bayesian inference is intractable for neural networks, however several approximate methods have been proposed. We experiment with three such methods using various uncertainty sampling active learning query strategies.
|
|
|
Evolutionary Design of Image Classifier
Koči, Martin ; Bidlo, Michal (referee) ; Drahošová, Michaela (advisor)
This thesis deals with evolutionary design of image classifier with help of genetic programming, specifically with cartesian genetic programming. Thesis discribes teoretical basics of machine learing, evolutionary algorithms and genetic programming. Part of this thesis is described design of the program and its implementation. Futhermore, experiments are performed on two solved tasks for the classification of handwritten digits and the classification of cube drawings, which can be used to determine the rate of dementia in Parkinson's disease. The best designed solution for digits is with AUC of 0.95 and for cubes 0.86. Designed solutions are compared by other methods, namely convolutional neural networks (CNN) and the support vector machines (SVM). The resulting AUC for the classification of digits for both CNN and SVM is 0.99, for cubes CNN has a final AUC 0.81 and SVM 0.69. The cubes are then compared with existing solution, which resulted in AUC 0.70, so that the results of the experiments show an improvement in the method used in this thesis.
|
|
|
Right Convolutional Neural Network For Classification Illustrations In Artworks
Sikora, Pavel
This paper deals with the image classification problem in the field of artworks. The articleuses a custom dataset from artworks with eight classes of some not common objects and illustrations.This dataset is used to train three convolutional neural networks for classification. All classificationresults are well discussed and evaluated with an example on the images from a dataset.
|
|
|
Urban Element Detection Using Satellite Imagery
Oravec, Dávid ; Herout, Adam (referee) ; Zlámal, Adam (advisor)
Táto práca sa zameriava na správnu detekciu objektov v satelitných snímkach pomocou konvolučných neuronových sietí. Cieľom práce je pomocou natrénovaného modelu detekovať bazény a tenisové ihriská v satelitných snímkach z rôznych miest. Model pracuje s dátami z 10 rôznych miest. Pri vypracovaní bol využitý model neurónovej siete RetinaNet a knižnica Detectron2. Model, ktorý sa podarilo vytrénovať, dokáže detekovať objekty s priemernou presnosťou (AP50) na úrovni 63,402 %. Práca môže byť prínosom v oblasti automatizovania získavania štatistík o povrchu zeme.
|
|
|
Tumor cell classification using deep-learning
Majerčík, Jakub ; Kolář, Radim (referee) ; Vičar, Tomáš (advisor)
Classification of microscopic cancer cell images finds its use in a wide variety of biological and medical applications. This work aims to classify two lines of aggressive tumor prostate cells with induced zinc resistance using deep learning methods, and provide an interpretation of occurring classification processes. Dataset consists of more than 750 images, whose acquisition was performed using optical diffraction tomography. This microscopy method allowed for non-invasive cell imaging in their native state. This work shows an implementation of a convolutional neural network, along with methods for visualization of classification processes used to generate localization maps (Grad-CAM and an occlusion-based method). The neural network classifies two prostate cell lines used in study with an accuracy of 98,08% and the aggressive zinc-resistance phenotype with an accuracy of 96,08%. Localization maps and manual segmentation masks of cell borders, nuclei and nucleoli allowed for analysis of sub-celullar regions, which indicates that the decisive region for correct classification is the region of cytoplasm. This is most likely the result of variable vesicle count in cytoplasm, their size, as well as the overall cell size and the morfological structure of their cytoplasmic membrane depending on a given phenotype.
|
|
|
Object detection in video using neural networks and Android application
Mikulec, Vojtěch ; Kiac, Martin (referee) ; Myška, Vojtěch (advisor)
This master’s thesis deals with the implementation of functional solution for classifying road users using mobile device with Android operating system. The goal is to create Android application which classifies vehicles in real time using rear-facing camera and saves timestamps of classification. Testing is performed mostly with own, diversely modificated dataset. Five models are trained and their performance is measured in dependence on hardware. The best classification performance is from pretrained MobileNet model where transfer learning with 6 classes of own dataset is used – 62,33 %. The results are summarized and a method for faster and more accurate traffic analysis is proposed.
|
|
|
Texture modeling applied to medical images
Remeš, Václav ; Haindl, Michal (advisor)
and contributions This thesis presents novel descriptive multidimensional Markovian textural models applied to computer aided diagnosis in the field of X-ray mammogra- phy. These general mathematical models, applicable in wide areas of texture modeling outside X-ray mammography as well, provide ideal visual verification using synthesis of the corresponding measured data spaces, contrary to stan- dard discriminative models. All achieved results in the thesis are extensively benchmarked. The thesis presents two methods for breast density classification in X-ray mammography. The methods were tested on the widely known MIAS database and the state-of-the art INbreast database, with competitive results. Several methods for completely automatic mammogram texture enhance- ment are presented. These methods are based on the descriptive textural mod- els developed in the thesis which automatically adapt to the analyzed X-ray texture, thus being universal for any type of input without the need of further manual tuning of specific parameters. The methods' outputs highlight regions of interest, detected as textural abnormalities. The methods provide the pos- sibility of enhancement tuned to specific types of mammogram tissue. Hence, the enhanced mammograms can help radiologists to decrease their false negative...
|
|
|
Statistical image analysis in quality control
Legát, David
Title: Statistical image analysis in quality control Author: David Legát Department: Department of probability and mathematical statistics Supervisor: Prof. RNDr. Jaromír Antoch, CSc. Abstract: Currently, necessity to handle unstructured data rises significantly. One important area of unstructured data manipulation is signal processing such as audio and video, for which there exist many procedures. This work deals with the statistical approach to image processing, in which the image is interpreted as a representative of a random field. It describes two problems: removing noise from an image which facilitates better interpretation of the image, and image classification, in which we try to identify and recognize objects displayed. Part of the work aimed at eliminating of noise deals primarily with the use of MCMC simulation methods. These procedures can be tested in software that is included. Part of the work dealing with the classification of the image describes various modifications of classification trees methods. An example of image processing, which is the identification of defects in woven fabrics, is presented at the end. 1
|
guest ::
