Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • 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
Noise Reduction in Flash X-ray Imaging Using Deep Learning
Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Scientific Computing.
2018 (English)Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Recent improvements in deep learning architectures, combined with the strength of modern computing hardware such as graphics processing units, has lead to significant results in the field of image analysis. In this thesis work, locally connected architectures are employed to reduce noise in flash X-ray diffraction images. The layers in these architectures use convolutional kernels, but without shared weights. This combines the benefits of lower model memory footprint in convolutional networks with the higher model capacity of fully connected networks. Since the camera used to capture the diffraction images has pixelwise unique characteristics, and thus lacks equivariance, this compromise can be beneficial.

The background images of this thesis work were generated with an active laser but without injected samples. Artificial diffraction patterns were then added to these background images allowing for training U-Net architectures to separate them. Architecture A achieved a performance of 0.187 on the test set, roughly translating to 35 fewer photon errors than a model similar to state of the art. After smoothing the photon errors this performance increased to 0.285, since the U-Net architectures managed to remove flares where state of the art could not. This could be taken as a proof of concept that locally connected networks are able to separate diffraction from background in flash X-Ray imaging.

Place, publisher, year, edition, pages
2018. , p. 57
Series
UPTEC F, ISSN 1401-5757 ; 18047
Keywords [en]
flash x-ray imaging, machine learning, deep learning, neural network, locally connected layer, autoencoder, LCLS, GPU, tensorflow, python, U-Net, free electron laser, selu, scaled exponential linear unit, diffraction, simulation, residual, concatenation
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:uu:diva-355731OAI: oai:DiVA.org:uu-355731DiVA, id: diva2:1230565
Educational program
Master Programme in Engineering Physics
Supervisors
Examiners
Available from: 2018-07-04 Created: 2018-07-03 Last updated: 2018-07-04Bibliographically approved

Open Access in DiVA

thesis_text(35275 kB)36 downloads
File information
File name FULLTEXT01.pdfFile size 35275 kBChecksum SHA-512
5476601409fd24074d6c2069459909342fc666fd40a573faf3857311458458685913247fda98e3ea85d3c140ae4c19143ce3ca540365dfb3fe184f9d538401cf
Type fulltextMimetype application/pdf

By organisation
Division of Scientific Computing
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 36 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: 308 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • 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