Cargando…

Intelligent compression for synchrotron radiation source image

<!--HTML-->Synchrotron radiation sources (SRS) produce a huge amount of image data. This scientific data, which needs to be stored and transferred losslessly, will bring great pressure on storage and bandwidth. The SRS images have the characteristics of high frame rate and high resolution, and...

Descripción completa

Detalles Bibliográficos
Autor principal: Fu, Shiyuan
Lenguaje:eng
Publicado: 2021
Materias:
Acceso en línea:http://cds.cern.ch/record/2766905
_version_ 1780971247138504704
author Fu, Shiyuan
author_facet Fu, Shiyuan
author_sort Fu, Shiyuan
collection CERN
description <!--HTML-->Synchrotron radiation sources (SRS) produce a huge amount of image data. This scientific data, which needs to be stored and transferred losslessly, will bring great pressure on storage and bandwidth. The SRS images have the characteristics of high frame rate and high resolution, and traditional image lossless compression methods can only save up to 30% in size. Focus on this problem, we propose a lossless compression method for SRS images based on deep learning. First, we use the difference algorithm to reduce the linear correlation within the image sequence. Then we propose a reversible truncated mapping method to reduce the range of the pixel value distribution. Thirdly, we train a deep learning model to learn the nonlinear relationship within the image sequence. Finally, we use the probability distribution predicted by the deep leaning model combined with arithmetic coding to fulfil lossless compression. Test result based on SRS images shows that our method can further decrease 20% of the data size compared to PNG, JPEG2000 and FLIF.
id cern-2766905
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2021
record_format invenio
spelling cern-27669052022-11-02T22:25:53Zhttp://cds.cern.ch/record/2766905engFu, ShiyuanIntelligent compression for synchrotron radiation source image25th International Conference on Computing in High Energy & Nuclear PhysicsConferences<!--HTML-->Synchrotron radiation sources (SRS) produce a huge amount of image data. This scientific data, which needs to be stored and transferred losslessly, will bring great pressure on storage and bandwidth. The SRS images have the characteristics of high frame rate and high resolution, and traditional image lossless compression methods can only save up to 30% in size. Focus on this problem, we propose a lossless compression method for SRS images based on deep learning. First, we use the difference algorithm to reduce the linear correlation within the image sequence. Then we propose a reversible truncated mapping method to reduce the range of the pixel value distribution. Thirdly, we train a deep learning model to learn the nonlinear relationship within the image sequence. Finally, we use the probability distribution predicted by the deep leaning model combined with arithmetic coding to fulfil lossless compression. Test result based on SRS images shows that our method can further decrease 20% of the data size compared to PNG, JPEG2000 and FLIF.oai:cds.cern.ch:27669052021
spellingShingle Conferences
Fu, Shiyuan
Intelligent compression for synchrotron radiation source image
title Intelligent compression for synchrotron radiation source image
title_full Intelligent compression for synchrotron radiation source image
title_fullStr Intelligent compression for synchrotron radiation source image
title_full_unstemmed Intelligent compression for synchrotron radiation source image
title_short Intelligent compression for synchrotron radiation source image
title_sort intelligent compression for synchrotron radiation source image
topic Conferences
url http://cds.cern.ch/record/2766905
work_keys_str_mv AT fushiyuan intelligentcompressionforsynchrotronradiationsourceimage
AT fushiyuan 25thinternationalconferenceoncomputinginhighenergynuclearphysics