|
|
A Library for Convolutional Neural Network Design
Rek, Petr ; Mrázek, Vojtěch (referee) ; Sekanina, Lukáš (advisor)
In this diploma thesis, the reader is introduced to artificial neural networks and convolutional neural networks. Based on that, the design and implementation of a new library for convolutional neural networks is described. The library is then evaluated on widely used datasets and compared to other publicly available libraries. The added benefit of the library, that makes it unique, is its independence on data types. Each layer may contain up to three independent data types - for weights, for inference and for training. For the purpose of evaluating this feature, a data type with fixed point representation is also part of the library. The effects of this representation on trained net accuracy are put to a test.
|
|
|
Convolutional Neural Networks
Lietavcová, Zuzana ; Zbořil, František (referee) ; Zbořil, František (advisor)
This thesis deals with convolutional neural networks. It is a kind of deep neural networks that are presently widely used mainly for image recognition and natural language processing. The thesis describes specifics of convolutional neural networks in comparison with traditional neural networks and is focused on inner computations in the process of learning. Convolutional neural networks typically consist of a different types of layers of neurons and the core part of this thesis is to demonstrate computations of individual types of layers. Learning demonstrating program of a simple convolutional network was designed and implemented using own implementation of neural network. Validity of the implementation was tested by training models for solving a classification task. Experiments with different types of architectures were conducted and their performance was compared.
|
|
| |
|
|
Detection, Tracking and Classification of Vehicles
Vopálenský, Radek ; Sochor, Jakub (referee) ; Juránek, Roman (advisor)
The aim of this master thesis is to design and implement a system for the detection, tracking and classification of vehicles from streams or records from traffic cameras in language C++. The system runs on the platform Robot Operating System and uses the OpenCV, FFmpeg, TensorFlow and Keras libraries. For detection cascade classifier is used, for tracking Kalman filter and for classification of the convolutional neural network. Out of a total of 627 cars, 479 were tracked correctly. From this number 458 were classified (trucks or lorries not included). The resulting system can be used for traffic 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.
|
|
|
A convolutional neural network for image segmentation
Mitrenga, Michal ; Petyovský, Petr (referee) ; Jirsík, Václav (advisor)
The aim of the bachelor thesis is to learn more about the problem of convolutional neural networks and to realize image segmentation. This theme includes the field of computer vision, which is used in systems of artificial intelligence. Special Attention is paid to the image segmentation process. Furthermore, the thesis deals with the basic principles of artificial neural networks, the structure of convolutional neural networks and especially with the description of individual semantic segmentation architectures. The chosen SegNet architecture is used in a practical application along with a pre-learned network. Part of the work is a database of CamVid images, which is used for training. For testing, a custom image database is created. Practical part is focused on CNN training and searching for unsuitable parameters for network learning using SW Matlab.
|
|
|
Reinforcement learning for solving game algorithms
Daňhelová, Jana ; Uher, Václav (referee) ; Kolařík, Martin (advisor)
The bachelor thesis Reinforcement learning for solving game algorithms is divided into two distinct parts. The theoretical part describes and compares the fundamental methods of reinforcement learning with special attention to the methods of active learning – Q-learning and deep learning. In the practical part the deep q-learning technique is chosen for testing and applied to the case of the Snake game. The results are presented in the form of program written in Python programming language, which consists of the game environment created in PyGame, the model of convolutional neural network designed in Keras and agent playing the game. As an output of the program there are several types of datasets in CSV format. The gained data containing the values of parameters like number of epochs, accuracy, loss or the amount of the reward can later be used for further processing.
|
|
|
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.
|
|
|
Protection of sensitive data contained in images
Mezina, Anzhelika ; Rajnoha, Martin (referee) ; Burget, Radim (advisor)
Tato bakalářská práce je zaměřena na využití hlubokého učení v bezpečnostním problému úniku citlivých informací ve formě obrazových dat. Pokusem o vyřešení tohoto problému bylo použití Single Shot Multibox Detectoru (SSD) a plně propojené sítě, poslední je mnohem rychlejší než jiné metody a může být použitá v praxi, kde je potřeba velmi rychlé analýzy příchozí a odchozí informace, například analýzy provozu sítě. V první části práce jsou popsané metody, které mohou být použité pro detekci klíčových slov. Druhá část obsahuje popis experimentu a dosažených výsledků pro dva modely neuronových sítí: Single Shot Multibox Detector a plně propojené sítě. Druhý model dosahuje uspokojivých vlastností jak z pohledu času zpracování tak i přesnosti a lze jej použít v praxi.
|
|
|
Traffic Light Detection in Image
Boček, Václav ; Jirsík, Václav (referee) ; Horák, Karel (advisor)
This bachelor thesis deals with the traffic lights detection and recognition of the displayed colour using methods of machine learning. In the theoretical section, different methods to solve this problem are described. The practical part describes the proposed system which was realized using convolutional neural networks. Furthermore, results of performed tests are shown.
|
guest ::
