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

Norikazu Takahashi; Ken Ishitobi; Tetsuo Nishi

doi:10.1109/iscas.2007.378101

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

Norikazu Takahashi, Ken Ishitobi, Tetsuo Nishi

Research output: Contribution to journal › Conference article › peer-review

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 language	English
Article number	4253349
Pages (from-to)	3159-3162
Number of pages	4
Journal	Proceedings - IEEE International Symposium on Circuits and Systems
DOIs	https://doi.org/10.1109/iscas.2007.378101
Publication status	Published - Jan 1 2007
Externally published	Yes
Event	2007 IEEE International Symposium on Circuits and Systems, ISCAS 2007 - New Orleans, LA, United States Duration: May 27 2007 → May 30 2007

ASJC Scopus subject areas

Electrical and Electronic Engineering

Access to Document

10.1109/iscas.2007.378101

Cite this

@article{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",

month = jan,

day = "1",

doi = "10.1109/iscas.2007.378101",

language = "English",

pages = "3159--3162",

journal = "Proceedings - IEEE International Symposium on Circuits and Systems",

issn = "0271-4310",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "2007 IEEE International Symposium on Circuits and Systems, ISCAS 2007 ; Conference date: 27-05-2007 Through 30-05-2007",

}

TY - JOUR

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 - 2007/1/1

Y1 - 2007/1/1

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

U2 - 10.1109/iscas.2007.378101

DO - 10.1109/iscas.2007.378101

M3 - Conference article

AN - SCOPUS:34548828556

SN - 0271-4310

SP - 3159

EP - 3162

JO - Proceedings - IEEE International Symposium on Circuits and Systems

JF - Proceedings - IEEE International Symposium on Circuits and Systems

M1 - 4253349

T2 - 2007 IEEE International Symposium on Circuits and Systems, ISCAS 2007

Y2 - 27 May 2007 through 30 May 2007

ER -

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

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this