Deblurring of images by cellular neural networks with applications to microscopy

John P. Miller, T. Roska, T. Szirányi, Kenneth R. Crounse, Leon O. Chua, L. Nemes

Research output: Conference contribution

13 Citations (Scopus)

Abstract

In this paper it is shown how the Cellular Neural Network (CNN) can be used to perform image and volume deblurring, with particular emphasis on applications to microscopy. We discuss the basic linear theory of the CNN including issues of stability and template size. It is observed that a CNN with a small template can be used to implement an Infinite Impulse Response filter. It is then shown how general deblurring problems can be addressed with a CNN when the blurring operator is known. The proposed application is to solve the basic 3-D confocal image reconstruction task of microscopy in real-time. It will be shown that under a reasonable sampling assumption about the form of the blurring operator, confocal behavior in microscope images can be obtained with only 3-5 acquired image planes. In addition, the stored program capability of the CNN Universal Machine would provide integration of several image processing and detection tasks in the same architecture.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications
PublisherIEEE
Pages237-242
Number of pages6
Publication statusPublished - 1994
EventProceedings of the 3rd IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94) - Rome, Italy
Duration: dec. 18 1994dec. 21 1994

Other

OtherProceedings of the 3rd IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)
CityRome, Italy
Period12/18/9412/21/94

Fingerprint

Cellular neural networks
Microscopic examination
IIR filters
Image reconstruction
Mathematical operators
Image processing
Microscopes
Sampling

ASJC Scopus subject areas

  • Software

Cite this

Miller, J. P., Roska, T., Szirányi, T., Crounse, K. R., Chua, L. O., & Nemes, L. (1994). Deblurring of images by cellular neural networks with applications to microscopy. In Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications (pp. 237-242). IEEE.

Deblurring of images by cellular neural networks with applications to microscopy. / Miller, John P.; Roska, T.; Szirányi, T.; Crounse, Kenneth R.; Chua, Leon O.; Nemes, L.

Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. IEEE, 1994. p. 237-242.

Research output: Conference contribution

Miller, JP, Roska, T, Szirányi, T, Crounse, KR, Chua, LO & Nemes, L 1994, Deblurring of images by cellular neural networks with applications to microscopy. in Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. IEEE, pp. 237-242, Proceedings of the 3rd IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94), Rome, Italy, 12/18/94.
Miller JP, Roska T, Szirányi T, Crounse KR, Chua LO, Nemes L. Deblurring of images by cellular neural networks with applications to microscopy. In Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. IEEE. 1994. p. 237-242
Miller, John P. ; Roska, T. ; Szirányi, T. ; Crounse, Kenneth R. ; Chua, Leon O. ; Nemes, L. / Deblurring of images by cellular neural networks with applications to microscopy. Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. IEEE, 1994. pp. 237-242
@inproceedings{739db84b620746eab8e09f062073d93d,
title = "Deblurring of images by cellular neural networks with applications to microscopy",
abstract = "In this paper it is shown how the Cellular Neural Network (CNN) can be used to perform image and volume deblurring, with particular emphasis on applications to microscopy. We discuss the basic linear theory of the CNN including issues of stability and template size. It is observed that a CNN with a small template can be used to implement an Infinite Impulse Response filter. It is then shown how general deblurring problems can be addressed with a CNN when the blurring operator is known. The proposed application is to solve the basic 3-D confocal image reconstruction task of microscopy in real-time. It will be shown that under a reasonable sampling assumption about the form of the blurring operator, confocal behavior in microscope images can be obtained with only 3-5 acquired image planes. In addition, the stored program capability of the CNN Universal Machine would provide integration of several image processing and detection tasks in the same architecture.",
author = "Miller, {John P.} and T. Roska and T. Szir{\'a}nyi and Crounse, {Kenneth R.} and Chua, {Leon O.} and L. Nemes",
year = "1994",
language = "English",
pages = "237--242",
booktitle = "Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications",
publisher = "IEEE",

}

TY - GEN

T1 - Deblurring of images by cellular neural networks with applications to microscopy

AU - Miller, John P.

AU - Roska, T.

AU - Szirányi, T.

AU - Crounse, Kenneth R.

AU - Chua, Leon O.

AU - Nemes, L.

PY - 1994

Y1 - 1994

N2 - In this paper it is shown how the Cellular Neural Network (CNN) can be used to perform image and volume deblurring, with particular emphasis on applications to microscopy. We discuss the basic linear theory of the CNN including issues of stability and template size. It is observed that a CNN with a small template can be used to implement an Infinite Impulse Response filter. It is then shown how general deblurring problems can be addressed with a CNN when the blurring operator is known. The proposed application is to solve the basic 3-D confocal image reconstruction task of microscopy in real-time. It will be shown that under a reasonable sampling assumption about the form of the blurring operator, confocal behavior in microscope images can be obtained with only 3-5 acquired image planes. In addition, the stored program capability of the CNN Universal Machine would provide integration of several image processing and detection tasks in the same architecture.

AB - In this paper it is shown how the Cellular Neural Network (CNN) can be used to perform image and volume deblurring, with particular emphasis on applications to microscopy. We discuss the basic linear theory of the CNN including issues of stability and template size. It is observed that a CNN with a small template can be used to implement an Infinite Impulse Response filter. It is then shown how general deblurring problems can be addressed with a CNN when the blurring operator is known. The proposed application is to solve the basic 3-D confocal image reconstruction task of microscopy in real-time. It will be shown that under a reasonable sampling assumption about the form of the blurring operator, confocal behavior in microscope images can be obtained with only 3-5 acquired image planes. In addition, the stored program capability of the CNN Universal Machine would provide integration of several image processing and detection tasks in the same architecture.

UR - http://www.scopus.com/inward/record.url?scp=0028738954&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028738954&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0028738954

SP - 237

EP - 242

BT - Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications

PB - IEEE

ER -