|
|
Trainable image segmentation using deep neural networks
Majtán, Martin ; Burget, Radim (referee) ; Harár, Pavol (advisor)
Diploma thesis is aimed to trainable image segmentation using deep neural networks. In the paper is explained the principle of digital image processing and image segmentation. In the paper is also explained the principle of artificial neural network, model of artificial neuron, training and activation of artificial neural network. In practical part of the paper is created an algorithm of sliding window to generate sub-images from image from magnetic rezonance. Generated sub-images are used to train, test and validate of the model of neural network. In practical part of the paper si created the model of the artificial neural network, which is used to trainable image segmentation. Model of the neural network is created using the Deeplearning4j library and it is optimized to parallel training using Spark library.
|
|
|
Client-Server Application Based on CORBA
Majtán, Martin ; Mašek, Jan (referee) ; Karásek, Jan (advisor)
Bachelor thesis deals with client-server applications and software technologies used to implement client-server applications in the Java programming language. The goal of bachelor thesis is the parallelization of genetic algorithm for knapsack problem and create two distributed models for technology CORBA and Hessian. In the teoretical part of the thesis are describes the basic concept of network communication, explanation client-server model of network communication, there are discussed technologies Java RMI, CORBA and Hessian. In the thesis is described the parallel and the distributed model of data processing, genetic algorithm and its use to solve the knapsack problem. In the practical part is created parallel and distributed model of a genetic algorithm for knapsack problem using technology CORBA and Hessian. In the thesis is done comparison of parallel model and distributed models in terms of calculation time. Results of measurement time are displayed in tables.
|
|
|
Trainable Image Segmentation Using Deep Neural Networks
Majtán, Martin
This paper is focused on trainable segmentation of image with use of deep neural networks. In this paper, the principle of creating images from magnetic resonance, generating data with algorithm of sliding window, creating a data set used for training neural network and principal segmentation of image with neural network is described. In practical part the algorithm of sliding window is created for generating data from magnetic resonance images and created model of artificial neural network used for image segmentation. In the practical part was achieved accuracy of segmentation 64 %.
|
|
|
Client-Server Application Based on CORBA
Majtán, Martin ; Mašek, Jan (referee) ; Karásek, Jan (advisor)
Bachelor thesis deals with client-server applications and software technologies used to implement client-server applications in the Java programming language. The goal of bachelor thesis is the parallelization of genetic algorithm for knapsack problem and create two distributed models for technology CORBA and Hessian. In the teoretical part of the thesis are describes the basic concept of network communication, explanation client-server model of network communication, there are discussed technologies Java RMI, CORBA and Hessian. In the thesis is described the parallel and the distributed model of data processing, genetic algorithm and its use to solve the knapsack problem. In the practical part is created parallel and distributed model of a genetic algorithm for knapsack problem using technology CORBA and Hessian. In the thesis is done comparison of parallel model and distributed models in terms of calculation time. Results of measurement time are displayed in tables.
|
|
|
Trainable image segmentation using deep neural networks
Majtán, Martin ; Burget, Radim (referee) ; Harár, Pavol (advisor)
Diploma thesis is aimed to trainable image segmentation using deep neural networks. In the paper is explained the principle of digital image processing and image segmentation. In the paper is also explained the principle of artificial neural network, model of artificial neuron, training and activation of artificial neural network. In practical part of the paper is created an algorithm of sliding window to generate sub-images from image from magnetic rezonance. Generated sub-images are used to train, test and validate of the model of neural network. In practical part of the paper si created the model of the artificial neural network, which is used to trainable image segmentation. Model of the neural network is created using the Deeplearning4j library and it is optimized to parallel training using Spark library.
|
guest ::
RSS feed.