Original title: Trainable Image Segmentation Using Deep Neural Networks
Authors: Majtán, Martin
Document type: Papers
Language: slo
Publisher: Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií
Abstract: 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 %.
Keywords: deep learning; DL4J; MRI; multiple sclerosis; neural network; segmentation
Host item entry: Proceedings of the 22nd Conference STUDENT EEICT 2016, ISBN 978-80-214-5350-0

Institution: Brno University of Technology (web)
Document availability information: Fulltext is available in the Brno University of Technology Digital Library.
Original record: http://hdl.handle.net/11012/83909

Permalink: http://www.nusl.cz/ntk/nusl-383627


The record appears in these collections:
Universities and colleges > Public universities > Brno University of Technology
Conference materials > Papers