Using unaltered, variable sized and high-resolution images for training fully-convolutional networks

Using unaltered, variable sized and high-resolution images for training fully-convolutional networks

Motivated by the usefulness of high resolution images in a broad range of applications, such as medical imaging, astronomy and video surveillance, in this thesis we investigate training a convolutions neural network with unaltered high-resolution images.

Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Fourkioti, Olga
Format: Dissertation
Sprache:eng
Schlagworte:
convolutional neural networks
high resolution
Imaging systems
Imatgeria (Tècnica)
Informàtica
Neural networks (Computer science)
variable sized images
Xarxes neuronals (Informàtica)
Àrees temàtiques de la UPC
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Motivated by the usefulness of high resolution images in a broad range of applications, such as medical imaging, astronomy and video surveillance, in this thesis we investigate training a convolutions neural network with unaltered high-resolution images.