Spatio-temporal CNN algorithm for object segmentation and object recognition

Abraham Schultz, Csaba Rekeczky, Istvan Szatmari, T. Roska, Leon O. Chua

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

7 Citations (Scopus)

Abstract

In this paper a spatio-temporal analogic CNN algorithm is designed for front-end filtering, segmentation and object recognition. First, a generalized segmentation strategy is presented based on various diffusion models. Both PDE and non-PDE related schemes are discussed and their VLSI complexity is analyzed. In classification (object recognition) a CNN implementation of the autowave metric, a `nonlinear' variant of the Hausdorff metric, is used. This approach turned out to be superior compared to some other classification methods, e.g. the Hamming distance calculation. A number of tests have been completed within the so-called `bubble/debris' segmentation experiments using original and artificial gray-scale images.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications
EditorsV. Tavsanoglu
PublisherIEEE
Pages347-352
Number of pages6
Publication statusPublished - 1998
EventProceedings of the 1998 5th IEEE International Workshop on Cellular Neural Networks and Their Applications, CNNA - London, UK
Duration: Apr 14 1998Apr 17 1998

Other

OtherProceedings of the 1998 5th IEEE International Workshop on Cellular Neural Networks and Their Applications, CNNA
CityLondon, UK
Period4/14/984/17/98

Fingerprint

Object recognition
Hamming distance
Debris
Experiments

ASJC Scopus subject areas

  • Software

Cite this

Schultz, A., Rekeczky, C., Szatmari, I., Roska, T., & Chua, L. O. (1998). Spatio-temporal CNN algorithm for object segmentation and object recognition. In V. Tavsanoglu (Ed.), Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications (pp. 347-352). IEEE.

Spatio-temporal CNN algorithm for object segmentation and object recognition. / Schultz, Abraham; Rekeczky, Csaba; Szatmari, Istvan; Roska, T.; Chua, Leon O.

Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. ed. / V. Tavsanoglu. IEEE, 1998. p. 347-352.

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

Schultz, A, Rekeczky, C, Szatmari, I, Roska, T & Chua, LO 1998, Spatio-temporal CNN algorithm for object segmentation and object recognition. in V Tavsanoglu (ed.), Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. IEEE, pp. 347-352, Proceedings of the 1998 5th IEEE International Workshop on Cellular Neural Networks and Their Applications, CNNA, London, UK, 4/14/98.
Schultz A, Rekeczky C, Szatmari I, Roska T, Chua LO. Spatio-temporal CNN algorithm for object segmentation and object recognition. In Tavsanoglu V, editor, Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. IEEE. 1998. p. 347-352
Schultz, Abraham ; Rekeczky, Csaba ; Szatmari, Istvan ; Roska, T. ; Chua, Leon O. / Spatio-temporal CNN algorithm for object segmentation and object recognition. Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. editor / V. Tavsanoglu. IEEE, 1998. pp. 347-352
@inproceedings{64755c86750d4e0f94aeb227d05d05bb,
title = "Spatio-temporal CNN algorithm for object segmentation and object recognition",
abstract = "In this paper a spatio-temporal analogic CNN algorithm is designed for front-end filtering, segmentation and object recognition. First, a generalized segmentation strategy is presented based on various diffusion models. Both PDE and non-PDE related schemes are discussed and their VLSI complexity is analyzed. In classification (object recognition) a CNN implementation of the autowave metric, a `nonlinear' variant of the Hausdorff metric, is used. This approach turned out to be superior compared to some other classification methods, e.g. the Hamming distance calculation. A number of tests have been completed within the so-called `bubble/debris' segmentation experiments using original and artificial gray-scale images.",
author = "Abraham Schultz and Csaba Rekeczky and Istvan Szatmari and T. Roska and Chua, {Leon O.}",
year = "1998",
language = "English",
pages = "347--352",
editor = "V. Tavsanoglu",
booktitle = "Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications",
publisher = "IEEE",

}

TY - GEN

T1 - Spatio-temporal CNN algorithm for object segmentation and object recognition

AU - Schultz, Abraham

AU - Rekeczky, Csaba

AU - Szatmari, Istvan

AU - Roska, T.

AU - Chua, Leon O.

PY - 1998

Y1 - 1998

N2 - In this paper a spatio-temporal analogic CNN algorithm is designed for front-end filtering, segmentation and object recognition. First, a generalized segmentation strategy is presented based on various diffusion models. Both PDE and non-PDE related schemes are discussed and their VLSI complexity is analyzed. In classification (object recognition) a CNN implementation of the autowave metric, a `nonlinear' variant of the Hausdorff metric, is used. This approach turned out to be superior compared to some other classification methods, e.g. the Hamming distance calculation. A number of tests have been completed within the so-called `bubble/debris' segmentation experiments using original and artificial gray-scale images.

AB - In this paper a spatio-temporal analogic CNN algorithm is designed for front-end filtering, segmentation and object recognition. First, a generalized segmentation strategy is presented based on various diffusion models. Both PDE and non-PDE related schemes are discussed and their VLSI complexity is analyzed. In classification (object recognition) a CNN implementation of the autowave metric, a `nonlinear' variant of the Hausdorff metric, is used. This approach turned out to be superior compared to some other classification methods, e.g. the Hamming distance calculation. A number of tests have been completed within the so-called `bubble/debris' segmentation experiments using original and artificial gray-scale images.

UR - http://www.scopus.com/inward/record.url?scp=0031618044&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031618044&partnerID=8YFLogxK

M3 - Conference contribution

SP - 347

EP - 352

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

A2 - Tavsanoglu, V.

PB - IEEE

ER -