|
|
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.
|
|
|
Blood vessel segmentation in retinal images using deep learning approaches
Serečunová, Stanislava ; Vičar, Tomáš (referee) ; Kolář, Radim (advisor)
This diploma thesis deals with the application of deep neural networks with focus on image segmentation. The theoretical part contains a description of deep neural networks and a summary of widely used convolutional architectures for segmentation of objects from the image. Practical part of the work was devoted to testing of an existing network architectures. For this purpose, an open-source software library Tensorflow, implemented in Python programming language, was used. A frequent problem incorporating the use of convolutional neural networks is the requirement on large amount of input data. In order to overcome this obstacle a new data set, consisting of a combination of five freely available databases was created. The selected U-net network architecture was tested by first modification of the newly created data set. Based on the test results, the chosen network architecture has been modified. By these means a new network has been created achieving better performance in comparison to the original network. The modified architecture is then trained on a newly created data set, that contains images of different types taken with various fundus cameras. As a result, the trained network is more robust and allows segmentation of retina blood vessels from images with different parameters. The modified architecture was tested on the STARE, CHASE, and HRF databases. Results were compared with published segmentation methods from literature, which are based on convolutional neural networks, as well as classical segmentation methods. The created network shows a high success rate of retina blood vessels segmentation comparable to state-of-the-art methods.
|
|
|
Superresulution of photography using deep neural network
Holub, Jiří ; Přinosil, Jiří (referee) ; Burget, Radim (advisor)
This diploma thesis deals with image super-resolution with conservation of good quality. Firstly, there are described state of the art methods dealing with this problem, as well as principles of neural networks with focus on convolutional ones. Finally, there is described a few models of convolutional neural network for image super-resolution to double size, which have been trained, tested and compared on newly created database with pictures of people.
|
|
|
Image similarity measuring using deep learning
Štarha, Dominik ; Šeda, Pavel (referee) ; Rajnoha, Martin (advisor)
This master´s thesis deals with the reseach of technologies using deep learning method, being able to use when processing image data. Specific focus of the work is to evaluate the suitability and effectiveness of deep learning when comparing two image input data. The first – theoretical – part consists of the introduction to neural networks and deep learning. Also, it contains a description of available methods, their benefits and principles, used for processing image data. The second - practical - part of the thesis contains a proposal a appropriate model of Siamese networks to solve the problem of comparing two input image data and evaluating their similarity. The output of this work is an evaluation of several possible model configurations and highlighting the best-performing model parameters.
|
|
|
Recurrent Neural Network for Text Classification
Myška, Vojtěch ; Kolařík, Martin (referee) ; Povoda, Lukáš (advisor)
Thesis deals with the proposal of the neural networks for classification of positive and negative texts. Development took place in the Python programming language. Design of deep neural network models was performed using the Keras high-level API and the TensorFlow numerical computation library. The computations were performed using GPU with support of the CUDA architecture. The final outcome of the thesis is linguistically independent neural network model for classifying texts at character level reaching up to 93,64% accuracy. Training and testing data were provided by multilingual and Yelp databases. The simulations were performed on 1200000 English, 12000 Czech, German and Spanish texts.
|
|
|
Image based flower recognition
Jedlička, František ; Kříž, Petr (referee) ; Přinosil, Jiří (advisor)
This paper is focus on flowers recognition in an image and class classification. Theoretical part is focus on problematics of deep convolutional neural networks. The practical part if focuse on created flowers database, with which it is further worked on. The database conteins it total 13000 plant pictures of 26 spicies as cornflower, violet, gerbera, cha- momile, cornflower, liverwort, hawkweed, clover, carnation, lily of the valley, marguerite daisy, pansy, poppy, marigold, daffodil, dandelion, teasel, forget-me-not, rose, anemone, daisy, sunflower, snowdrop, ragwort, tulip and celandine. Next is in the paper described used neural network model Inception v3 for class classification. The resulting accuracy has been achieved 92%.
|
|
|
Parallel Deep Learning
Šlampa, Ondřej ; Sochor, Jakub (referee) ; Hradiš, Michal (advisor)
Aim of this thesis is to propose how to evaluate favourableness of parallel deep learning. In this thesis I analyze parallel deep learning and I focus on its length. I take into account gradient computation length and weight transportation length. Result of this thesis is proposal of equations, which can estimate the speedup on multiple workers. These equations can be used to determine ideal number of workers for training.
|
|
|
Bayesian and Neural Networks
Hložek, Bohuslav ; Rozman, Jaroslav (referee) ; Zbořil, František (advisor)
This paper introduces Bayesian neural network based on Occams razor. Basic knowledge about neural networks and Bayes rule is summarized in the first part of this paper. Principles of Occams razor and Bayesian neural network are explained. A real case of use is introduced (about predicting landslide). The second part of this paper introduces how to construct Bayesian neural network in Python. Such an application is shown. Typical behaviour of Bayesian neural networks is demonstrated using example data.
|
|
|
Deep learning methods for image processing
Křenek, Jakub ; Chmelík, Jiří (referee) ; Kolář, Radim (advisor)
This master‘s thesis deals with the Deep Learning methods for image recognition tasks from the first methods to the modern ones. The main focus is on convolutional neural nets based models for classification, detection and image segmentation. These methods are used for practical implemetation – counting passing cars on video from traffic camera. After several test of available models, the YOLOv2 architecture was chosen and retrained on own dataset. The application also includes the addition of the SORT tracking algorithm.
|
|
|
Face detection and recognition with use of Raspberry Pi
Rozhoňová, Andrea ; Mézl, Martin (referee) ; Hesko, Branislav (advisor)
The following bachelor thesis is focused on the face detection and recognition in an image. The theoretical part divides methods of detection and recognition into several groups and there is better description and explanation of these methods in this part. At the end of the theoretical part is summarized the current utilization of person recognition on the bases of its face in practice. In the practical part is first implemented method for face detection. It is combination of two approaches - approach using haar features and approach using templates of eye. The face recognition is provided by the convolutional neural network. In conclusion there are summarized principles and problems associated with implementation on microcomputer Raspberry Pi and there is also evaluated the success of implemented methods.
|
guest ::
