|
|
Evolutionary Algorithms in Convolutional Neural Network Design
Badáň, Filip ; Vašíček, Zdeněk (referee) ; Sekanina, Lukáš (advisor)
This work focuses on automatization of neural network design via the so-called neuroevolution, which employs evolutionary algorithms to construct artificial neural networks or optimise their parameters. The goal of the project is to design and implement an evolutionary algorithm which can be used in the process of designing and optimizing topologies of convolutional neural networks. The effectiveness of the proposed framework was experimentally evaluated on tasks of image classification on datasets MNIST and CIFAR10 and compared with relevant solutions. The results showed that neuroevolution has a potential to successfully find accurate and effective convolutional neural network architectures.
|
|
|
Basics of Pedestrians Detection in Image by Machine Learning
Lučanský, Peter ; Klečka, Jan (referee) ; Horák, Karel (advisor)
Táto Bakalárska práce sa zaoberá významnou problematikou v oblasti počítačového videnia, ktorou je detekcia osôb/chodcov v obraze, za pomoci metod strojového učenia, spolu s jej možným využitím, vývojom a vysvetlením princípov. Taktiež sa zaoberá testovaním dnes najlepšieho dostupného algoritmu, pričom sa porovnávajú faktory ktoré vplívajú na kvalitu jeho činnosti. Na začiatku je problematika stručne popísaná, potom sa prejde k podrobným popisom dosiahnutých pokrokov. V nasledujúcej časti sú popísané dostupné datasety, ktoré by sa dali použiť pri tréningu detekčného algoritmu. V poslednom rade sú vykonané trénovacie procesy za rozličných podmienok, pričom sú jednotlivé výsledky porovnávané.
|
|
| |
|
|
Automatic 3D segmentation of brain images
Bafrnec, Matúš ; Dorazil, Jan (referee) ; Kolařík, Martin (advisor)
This bachelor thesis describes the design and implementation of the system for automatic 3D segmentation of a brain based on convolutional neural networks. The first part is dedicated to a brief history of neural networks and a theoretical description of the functionality of convolutional neural networks. It represents a fast introduction to the problematics and provides theoretical basics needed for the understanding and creation of the system. Individual layers of the neural network and principles of their functionality and mutual relations are also described in this part. The second part of the thesis is about problem analysis, designing of a solution and a comparison between neural networks and other solutions. The result of a magnetic resonance imaging of the head is a series of black-and-white images representing a 3D scan. The task is to tag a brain and to remove unnecessary information in the form of surrounding tissues. The final image of the brain can be utilized in a volumetry or during a diagnostic of neurodegenerative diseases. The advantage of neural networks in comparison with deterministic systems is their flexibility. They allow an adaptation to other segmentation problems just by changing the training dataset, without a need of changes in the architecture. One of the systems performing fully automatic 3D segmentation is called U-Net – its name comes from the similarity of the architecture with the letter U. Three real solutions, the first implementation of U-Net, extended U-Net and recurrent U-Net were presented. The first version of U-Net has been very memory-demanding, it required a training on a processor instead of a graphic card and has not allowed data processing in full resolution. The extended U-Net has resolved these problems by loading data in overlaying series of three images. In addition to the possibility of a training on a graphic card with related decrease in learning time, the accuracy was increased by adding interconnections to the internal architecture of the network. The last version, recurrent U-Net, aims for the optimization of extended U-Net based on the reusage of existing levels. This brings a decrease in a time and resource difficulty. The number of parameters of the network was lowered to less than 20%, without any increase in case of further level addition. This network is one of first recurrent networks used on the problem of 3D segmentation and provides a foundation to further research. The last part focuses on the evaluation of results and the comparison of accuracy, speed and requirements between particular networks. The accuracy of human and machine segmentation is also compared. The extended and recurrent U-Net have surpassed their human opponent, which in real case could save a lot of doctors time and prevent human mistakes. The result of this work is a theoretical basis providing an introduction to the problematics of convolutional neural networks and segmentation, fully working systems for automatic 3D segmentation and the foundation for further research in the field of recurrent networks.
|
|
|
Using machine learning for quality control in industrial applications
Gaško, Viktor ; Dobrovský, Ladislav (referee) ; Parák, Roman (advisor)
Goal of this bachelor´s thesis is to get acquainted with issue of quality control in industrial applications with focus on deep learning. For this and similar issues was created several libraries which have a purpose of simplifying these issues. Main task is to create program for quality control with help of programming language Python and framework Tensorflow. This program will be comprised of three neural network, from which one will identify the approximate position of the part, second its color, and third will check the correctness of its production.
|
|
|
Convolutional Networks for Handwriting Recognition
Sladký, Jan ; Kišš, Martin (referee) ; Hradiš, Michal (advisor)
This thesis deals with handwriting recognition using convolutional neural networks. From the current methods, a network model was chosen to consist of convolutional and recurrent neural networks with the Connectist Temporal Classification. The Vertical Attention Module, which selects the relevant information in each column corresponding to the text in the figure was subsequently implemented in such a model. Then, this module was compared with other possibilities of vertical aggregation between convolutional and recurrent networks. The experiments took place on a data set containing over 80,000 lines of text from Czech letters from the 20th century. The results show that the Vertical Attention Module almost always achieves the best results on all used types of convolution networks. The resulting network achieved the best result with 8,9% of the character error rate. The contribution of this work is a neural network with a newly introduced element that can recognize lines of text.
|
|
|
Road detection in outdoor environment using image processing
Vrbičanová, Antónia ; Věchet, Stanislav (referee) ; Krejsa, Jiří (advisor)
The Master’s thesis deals with the issue of the road detection in the outdoor environment using image processing. It is highly required that the methods selected are robust to sudden light changes within the image and effective in detection of wide variety of road surfaces possibly comprising certain kinds of pollution. Two methods have been used in order to reach the desired goal. The initial method uses standard algorithms of the image processing. Main outcome of this method are highlighted road boundaries. The following methodisbasedonconvolutionalneuralnetworks.Inthiscasewehaveclassificationtask. The result of this method is the estimation of the road direction. In the whole process, severalneuralnetworkstructureshavebeendesigned.Afterthenetworktrainingthemost suitable one was selected. Eventually, the results have been retested using newly created test set. Both of these methods are implemented in programming language Python.
|
|
|
Segmentation of brain tumours in MRI images using deep learning
Ustsinau, Usevalad ; Odstrčilík, Jan (referee) ; Chmelík, Jiří (advisor)
The following master's thesis paper equipped with a short description of CT scans and MR images and the main differences between them, explanation of the structure of convolutional neural networks and how they implemented into biomedical image analysis, besides it was taken a popular modification of U-Net and tested on two loss-functions. As far as segmentation quality plays a highly important role for doctors, in experiment part it was paid significant attention to training quality and prediction results of the model. The experiment has shown the effectiveness of the provided algorithm and performed 100 training cases with the following analysis through the similarity. The proposed outcome gives us certain ideas for future improving the quality of image segmentation via deep learning techniques.
|
|
|
Proportional counter measurement system
Kolář, Ondřej ; Matěj, Zdeněk (referee) ; Kubíček, Michal (advisor)
This work focuses on development of a measurment system for proportional counters that are used to measure ionizing radiation. The system allows for data acquisition from proportional counters in form of time waveforms for further analysis. Core of the system is a Red Pitaya STEMlab 125-14 board which is able to record fast signals and transfer them to a computer for further processing. The first part of this work briefly describes theory of ionizing radiation and propotional counters. In the following part the measuring unit and its improvements are described. The main part of this work is focused on development of new software and description of individual software pieces. In the last part a real measurement is depicted, gathered data are analyzed and a machine learning method is proposed as a solution for proportional counters data analysis.
|
|
|
Mobile Application Using Deep Convolutional Neural Networks
Poliak, Sebastián ; Herout, Adam (referee) ; Sochor, Jakub (advisor)
This thesis describes a process of creating a mobile application using deep convolutional neural networks. The process starts with proposal of the main idea, followed by product and technical design, implementation and evaluation. The thesis also explores the technical background of image recognition, and chooses the most suitable options for the purpose of the application. These are object detection and multi-label classification, which are both implemented, evaluated and compared. The resulting application tries to bring value from both user and technical point of view.
|
guest ::
