Sufficient conditions for 1-D CNNs with opposite-sign templates to perform connected component detection

Norikazu Takahashi, Ken Ishitobi, Tetsuo Nishi

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

1 Citation (Scopus)

Abstract

Connected component detection (CCD) is an important image processing task done by one-dimensional cellular neural networks (1-D CNNs). Recently, some sufficient conditions for 1-D CNNs with the antisymmetric template A = [s, p, - s] to perform CCD have been derived under the assumption that the outputs of the boundary cells are set to 1 or -1. In this paper, we extend these results to 1-D CNNs with the opposite-sign template A = [r, p, - s]. It is shown that the 1-D CNN can perform CCD for a wide range of parameter space. Therefore we can design 1-D CNNs which not only can perform CCD but also are robust against small perturbations of the parameters.

Original languageEnglish
Title of host publicationProceedings - IEEE International Symposium on Circuits and Systems
Pages3159-3162
Number of pages4
Publication statusPublished - 2007
Externally publishedYes
Event2007 IEEE International Symposium on Circuits and Systems, ISCAS 2007 - New Orleans, LA, United States
Duration: May 27 2007May 30 2007

Other

Other2007 IEEE International Symposium on Circuits and Systems, ISCAS 2007
CountryUnited States
CityNew Orleans, LA
Period5/27/075/30/07

Fingerprint

Cellular neural networks
Image processing

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Electrical and Electronic Engineering

Cite this

Takahashi, N., Ishitobi, K., & Nishi, T. (2007). Sufficient conditions for 1-D CNNs with opposite-sign templates to perform connected component detection. In Proceedings - IEEE International Symposium on Circuits and Systems (pp. 3159-3162). [4253349]

Sufficient conditions for 1-D CNNs with opposite-sign templates to perform connected component detection. / Takahashi, Norikazu; Ishitobi, Ken; Nishi, Tetsuo.

Proceedings - IEEE International Symposium on Circuits and Systems. 2007. p. 3159-3162 4253349.

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

Takahashi, N, Ishitobi, K & Nishi, T 2007, Sufficient conditions for 1-D CNNs with opposite-sign templates to perform connected component detection. in Proceedings - IEEE International Symposium on Circuits and Systems., 4253349, pp. 3159-3162, 2007 IEEE International Symposium on Circuits and Systems, ISCAS 2007, New Orleans, LA, United States, 5/27/07.
Takahashi N, Ishitobi K, Nishi T. Sufficient conditions for 1-D CNNs with opposite-sign templates to perform connected component detection. In Proceedings - IEEE International Symposium on Circuits and Systems. 2007. p. 3159-3162. 4253349
Takahashi, Norikazu ; Ishitobi, Ken ; Nishi, Tetsuo. / Sufficient conditions for 1-D CNNs with opposite-sign templates to perform connected component detection. Proceedings - IEEE International Symposium on Circuits and Systems. 2007. pp. 3159-3162
@inproceedings{0a4771f47cf94cb9b47a0d1750872392,
title = "Sufficient conditions for 1-D CNNs with opposite-sign templates to perform connected component detection",
abstract = "Connected component detection (CCD) is an important image processing task done by one-dimensional cellular neural networks (1-D CNNs). Recently, some sufficient conditions for 1-D CNNs with the antisymmetric template A = [s, p, - s] to perform CCD have been derived under the assumption that the outputs of the boundary cells are set to 1 or -1. In this paper, we extend these results to 1-D CNNs with the opposite-sign template A = [r, p, - s]. It is shown that the 1-D CNN can perform CCD for a wide range of parameter space. Therefore we can design 1-D CNNs which not only can perform CCD but also are robust against small perturbations of the parameters.",
author = "Norikazu Takahashi and Ken Ishitobi and Tetsuo Nishi",
year = "2007",
language = "English",
pages = "3159--3162",
booktitle = "Proceedings - IEEE International Symposium on Circuits and Systems",

}

TY - GEN

T1 - Sufficient conditions for 1-D CNNs with opposite-sign templates to perform connected component detection

AU - Takahashi, Norikazu

AU - Ishitobi, Ken

AU - Nishi, Tetsuo

PY - 2007

Y1 - 2007

N2 - Connected component detection (CCD) is an important image processing task done by one-dimensional cellular neural networks (1-D CNNs). Recently, some sufficient conditions for 1-D CNNs with the antisymmetric template A = [s, p, - s] to perform CCD have been derived under the assumption that the outputs of the boundary cells are set to 1 or -1. In this paper, we extend these results to 1-D CNNs with the opposite-sign template A = [r, p, - s]. It is shown that the 1-D CNN can perform CCD for a wide range of parameter space. Therefore we can design 1-D CNNs which not only can perform CCD but also are robust against small perturbations of the parameters.

AB - Connected component detection (CCD) is an important image processing task done by one-dimensional cellular neural networks (1-D CNNs). Recently, some sufficient conditions for 1-D CNNs with the antisymmetric template A = [s, p, - s] to perform CCD have been derived under the assumption that the outputs of the boundary cells are set to 1 or -1. In this paper, we extend these results to 1-D CNNs with the opposite-sign template A = [r, p, - s]. It is shown that the 1-D CNN can perform CCD for a wide range of parameter space. Therefore we can design 1-D CNNs which not only can perform CCD but also are robust against small perturbations of the parameters.

UR - http://www.scopus.com/inward/record.url?scp=34548828556&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548828556&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:34548828556

SP - 3159

EP - 3162

BT - Proceedings - IEEE International Symposium on Circuits and Systems

ER -