Picture segmentation with introducing an anisotropic preliminary step to an MRF model with cellular neural networks

T. Szirányi, László Czúni

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Due to the large computation power needed for Markovian random field (MRF) based image processing, new variations of the basic MRF model are implemented. The transportation of the model to the very fast cellular neural networks (CNN) gave new tasks and opportunities to improve the technique, since the CNN has a special local architecture. This CNN architecture can be implemented in real VLSI circuits of superior speed in image processing. A type of MRF image segmentation with modified metropolis dynamics (MMD) can be well implemented in the CNN architecture. In this paper we address the improvement of this existing CNN method by introducing anisotropic diffusion as the smoothing process in the model. We suggest that this new feature with the MRF representation will give a new approach to solving early vision problems in the future.

Original languageEnglish
Title of host publicationTrack D: Parallel and Connectionist Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages366-370
Number of pages5
Volume4
ISBN (Print)081867282X, 9780818672828
DOIs
Publication statusPublished - 1996
Event13th International Conference on Pattern Recognition, ICPR 1996 - Vienna, Austria
Duration: Aug 25 1996Aug 29 1996

Other

Other13th International Conference on Pattern Recognition, ICPR 1996
CountryAustria
CityVienna
Period8/25/968/29/96

Fingerprint

Cellular neural networks
Network architecture
Image processing
VLSI circuits
Image segmentation

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Szirányi, T., & Czúni, L. (1996). Picture segmentation with introducing an anisotropic preliminary step to an MRF model with cellular neural networks. In Track D: Parallel and Connectionist Systems (Vol. 4, pp. 366-370). [547447] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPR.1996.547447

Picture segmentation with introducing an anisotropic preliminary step to an MRF model with cellular neural networks. / Szirányi, T.; Czúni, László.

Track D: Parallel and Connectionist Systems. Vol. 4 Institute of Electrical and Electronics Engineers Inc., 1996. p. 366-370 547447.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Szirányi, T & Czúni, L 1996, Picture segmentation with introducing an anisotropic preliminary step to an MRF model with cellular neural networks. in Track D: Parallel and Connectionist Systems. vol. 4, 547447, Institute of Electrical and Electronics Engineers Inc., pp. 366-370, 13th International Conference on Pattern Recognition, ICPR 1996, Vienna, Austria, 8/25/96. https://doi.org/10.1109/ICPR.1996.547447
Szirányi T, Czúni L. Picture segmentation with introducing an anisotropic preliminary step to an MRF model with cellular neural networks. In Track D: Parallel and Connectionist Systems. Vol. 4. Institute of Electrical and Electronics Engineers Inc. 1996. p. 366-370. 547447 https://doi.org/10.1109/ICPR.1996.547447
Szirányi, T. ; Czúni, László. / Picture segmentation with introducing an anisotropic preliminary step to an MRF model with cellular neural networks. Track D: Parallel and Connectionist Systems. Vol. 4 Institute of Electrical and Electronics Engineers Inc., 1996. pp. 366-370
@inproceedings{d67a209dd0ce4ac5bb4ffb3939f7e8a5,
title = "Picture segmentation with introducing an anisotropic preliminary step to an MRF model with cellular neural networks",
abstract = "Due to the large computation power needed for Markovian random field (MRF) based image processing, new variations of the basic MRF model are implemented. The transportation of the model to the very fast cellular neural networks (CNN) gave new tasks and opportunities to improve the technique, since the CNN has a special local architecture. This CNN architecture can be implemented in real VLSI circuits of superior speed in image processing. A type of MRF image segmentation with modified metropolis dynamics (MMD) can be well implemented in the CNN architecture. In this paper we address the improvement of this existing CNN method by introducing anisotropic diffusion as the smoothing process in the model. We suggest that this new feature with the MRF representation will give a new approach to solving early vision problems in the future.",
author = "T. Szir{\'a}nyi and L{\'a}szl{\'o} Cz{\'u}ni",
year = "1996",
doi = "10.1109/ICPR.1996.547447",
language = "English",
isbn = "081867282X",
volume = "4",
pages = "366--370",
booktitle = "Track D: Parallel and Connectionist Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Picture segmentation with introducing an anisotropic preliminary step to an MRF model with cellular neural networks

AU - Szirányi, T.

AU - Czúni, László

PY - 1996

Y1 - 1996

N2 - Due to the large computation power needed for Markovian random field (MRF) based image processing, new variations of the basic MRF model are implemented. The transportation of the model to the very fast cellular neural networks (CNN) gave new tasks and opportunities to improve the technique, since the CNN has a special local architecture. This CNN architecture can be implemented in real VLSI circuits of superior speed in image processing. A type of MRF image segmentation with modified metropolis dynamics (MMD) can be well implemented in the CNN architecture. In this paper we address the improvement of this existing CNN method by introducing anisotropic diffusion as the smoothing process in the model. We suggest that this new feature with the MRF representation will give a new approach to solving early vision problems in the future.

AB - Due to the large computation power needed for Markovian random field (MRF) based image processing, new variations of the basic MRF model are implemented. The transportation of the model to the very fast cellular neural networks (CNN) gave new tasks and opportunities to improve the technique, since the CNN has a special local architecture. This CNN architecture can be implemented in real VLSI circuits of superior speed in image processing. A type of MRF image segmentation with modified metropolis dynamics (MMD) can be well implemented in the CNN architecture. In this paper we address the improvement of this existing CNN method by introducing anisotropic diffusion as the smoothing process in the model. We suggest that this new feature with the MRF representation will give a new approach to solving early vision problems in the future.

UR - http://www.scopus.com/inward/record.url?scp=84898782113&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898782113&partnerID=8YFLogxK

U2 - 10.1109/ICPR.1996.547447

DO - 10.1109/ICPR.1996.547447

M3 - Conference contribution

SN - 081867282X

SN - 9780818672828

VL - 4

SP - 366

EP - 370

BT - Track D: Parallel and Connectionist Systems

PB - Institute of Electrical and Electronics Engineers Inc.

ER -