liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Generative Adversarial Networks for Image-to-Image Translation on Street View and MR Images
Linköping University, Department of Biomedical Engineering.
Linköping University, Department of Biomedical Engineering.
2018 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Generative Adversarial Networks (GANs) is a deep learning method that has been developed for synthesizing data. One application for which it can be used for is image-to-image translations. This could prove to be valuable when training deep neural networks for image classification tasks. Two areas where deep learning methods are used are automotive vision systems and medical imaging. Automotive vision systems are expected to handle a broad range of scenarios which demand training data with a high diversity. The scenarios in the medical field are fewer but the problem is instead that it is difficult, time consuming and expensive to collect training data.

This thesis evaluates different GAN models by comparing synthetic MR images produced by the models against ground truth images. A perceptual study is also performed by an expert in the field. It is shown by the study that the implemented GAN models can synthesize visually realistic MR images. It is also shown that models producing more visually realistic synthetic images not necessarily have better results in quantitative error measurements, when compared to ground truth data. Along with the investigations on medical images, the thesis explores the possibilities of generating synthetic street view images of different resolution, light and weather conditions. Different GAN models have been compared, implemented with our own adjustments, and evaluated. The results show that it is possible to create visually realistic images for different translations and image resolutions.

Place, publisher, year, edition, pages
2018. , p. 76
Keywords [en]
Deep learning, Image processing, Artificial intelligence, Neural networks, MRI, Generative adversarial networks, Data augmentation, Image-to-image translation, Street view, Biomedical engineering, Electrical engineering
National Category
Medical Image Processing Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
URN: urn:nbn:se:liu:diva-148475ISRN: LIU-IMT-TFK-A—18/554—SEOAI: oai:DiVA.org:liu-148475DiVA, id: diva2:1216606
External cooperation
Institutionen för systemteknik, Department of Electrical Engineering; Veoneer
Subject / course
Medical Technology
Presentation
2018-06-08, IMT1, Ingång 65, Campus US, Linköping, 13:15 (English)
Supervisors
Examiners
Available from: 2018-06-12 Created: 2018-06-12 Last updated: 2018-06-12Bibliographically approved

Open Access in DiVA

fulltext(28302 kB)553 downloads
File information
File name FULLTEXT01.pdfFile size 28302 kBChecksum SHA-512
e31cf9e889596742044004b93e78d38d7c0170c588b2a398c57aa709ea8ee5938b1c18d9bd5bf9d5cfc28d7d7e8206ba530e9a22469b9c28d394591b4abe4eb5
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Karlsson, SimonWelander, Per
By organisation
Department of Biomedical Engineering
Medical Image ProcessingElectrical Engineering, Electronic Engineering, Information Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 553 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 2617 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf