Sparse representations for limited data tomography

Hstau Y. Liao; Guillermo Sapiro

doi:10.1109/ISBI.2008.4541261

Sparse representations for limited data tomography

Hstau Y. Liao, Guillermo Sapiro

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

45 Scopus citations

Abstract

In limited data tomography, with applications such as electron microscopy and medical imaging, the scanning views are within an angular range that is often both limited and sparsely sampled. In these situations, standard algorithms produce reconstructions with notorious artifacts. We show in this paper that a sparsity image representation principle, based on learning dictionaries for sparse representations of image patches, leads to significantly improved reconstructions of the unknown density from its limited angle projections. The presentation of the underlying framework is complemented with illustrative results on artificial and real data.

Original language	English (US)
Title of host publication	2008 5th IEEE International Symposium on Biomedical Imaging
Subtitle of host publication	From Nano to Macro, Proceedings, ISBI
Pages	1375-1378
Number of pages	4
DOIs	https://doi.org/10.1109/ISBI.2008.4541261
State	Published - 2008
Externally published	Yes
Event	2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI - Paris, France Duration: May 14 2008 → May 17 2008

Publication series

Name	2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI

Conference

Conference	2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI
Country/Territory	France
City	Paris
Period	5/14/08 → 5/17/08

All Science Journal Classification (ASJC) codes

Biomedical Engineering

Keywords

Limited angle tomography
Regularization
Sparse representations

Access to Document

10.1109/ISBI.2008.4541261

Cite this

@inproceedings{4f63418d9d6e4e73aaf2b21e23be1316,

title = "Sparse representations for limited data tomography",

abstract = "In limited data tomography, with applications such as electron microscopy and medical imaging, the scanning views are within an angular range that is often both limited and sparsely sampled. In these situations, standard algorithms produce reconstructions with notorious artifacts. We show in this paper that a sparsity image representation principle, based on learning dictionaries for sparse representations of image patches, leads to significantly improved reconstructions of the unknown density from its limited angle projections. The presentation of the underlying framework is complemented with illustrative results on artificial and real data.",

keywords = "Limited angle tomography, Regularization, Sparse representations",

author = "Liao, {Hstau Y.} and Guillermo Sapiro",

year = "2008",

doi = "10.1109/ISBI.2008.4541261",

language = "English (US)",

isbn = "9781424420032",

series = "2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI",

pages = "1375--1378",

booktitle = "2008 5th IEEE International Symposium on Biomedical Imaging",

note = "2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI ; Conference date: 14-05-2008 Through 17-05-2008",

}

Liao, HY & Sapiro, G 2008, Sparse representations for limited data tomography. in 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI., 4541261, 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI, pp. 1375-1378, 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI, Paris, France, 5/14/08. https://doi.org/10.1109/ISBI.2008.4541261

Sparse representations for limited data tomography. / Liao, Hstau Y.; Sapiro, Guillermo.
2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI. 2008. p. 1375-1378 4541261 (2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Sparse representations for limited data tomography

AU - Liao, Hstau Y.

AU - Sapiro, Guillermo

PY - 2008

Y1 - 2008

N2 - In limited data tomography, with applications such as electron microscopy and medical imaging, the scanning views are within an angular range that is often both limited and sparsely sampled. In these situations, standard algorithms produce reconstructions with notorious artifacts. We show in this paper that a sparsity image representation principle, based on learning dictionaries for sparse representations of image patches, leads to significantly improved reconstructions of the unknown density from its limited angle projections. The presentation of the underlying framework is complemented with illustrative results on artificial and real data.

AB - In limited data tomography, with applications such as electron microscopy and medical imaging, the scanning views are within an angular range that is often both limited and sparsely sampled. In these situations, standard algorithms produce reconstructions with notorious artifacts. We show in this paper that a sparsity image representation principle, based on learning dictionaries for sparse representations of image patches, leads to significantly improved reconstructions of the unknown density from its limited angle projections. The presentation of the underlying framework is complemented with illustrative results on artificial and real data.

KW - Limited angle tomography

KW - Regularization

KW - Sparse representations

UR - http://www.scopus.com/inward/record.url?scp=51049085785&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51049085785&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2008.4541261

DO - 10.1109/ISBI.2008.4541261

M3 - Conference contribution

AN - SCOPUS:51049085785

SN - 9781424420032

T3 - 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI

SP - 1375

EP - 1378

BT - 2008 5th IEEE International Symposium on Biomedical Imaging

T2 - 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI

Y2 - 14 May 2008 through 17 May 2008

ER -

Sparse representations for limited data tomography

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this