CNN-based difference-controlled adaptive non-linear image filters

Csaba Rekeczky, T. Roska, Akio Ushida

Research output: Contribution to journalArticle

54 Citations (Scopus)

Abstract

In this paper, we develop a common cellular neural network framework for various adaptive non-linear filters based on robust statistic and geometry-driven diffusion paradigms. The base models of both approaches are defined as difference-controlled non-linear CNN templates, while the self-adjusting property is ensured by simple analogic (analog and logic) CNN algorithms. Two adaptive strategies are shown for the order statistic class. When applied to the images distorted by impulse noise both give more visually pleasing results with lower-frequency weighted mean square error than the median base model. Generalizing a variational approach we derive the constrained anisotropic diffusion, where the output of the geometry-driven diffusion model is forced to stay close to a pre-defined morphological constraint. We propose a coarse-grid CNN approach that is capable of calculating an acceptable noise-level estimate (proportional to the variance of the Gaussian noise) and controlling the fine-grid anisotropic diffusion models. A combined geometrical-statistical approach has also been developed for filtering both the impulse and additive Gaussian noise while preserving the image structure. We briefly discuss how these methods can be embedded into a more complex algorithm performing edge detection and image segmentation. The design strategies are analysed primarily from VLSI implementation point of view; therefore all non-linear cell interactions of the CNN architecture are reduced to two fundamental non-linearities, to a sigmoid type and a radial basis function. The proposed non-linear characteristics can be approximated with simple piecewise-linear functions of the voltage difference of neighbouring cells. The simplification makes it possible to convert all space-invariant non-linear templates of this study to a standard instruction set of the CNN Universal Machine, where each instruction is coded by at most a dozen analog numbers. Examples and simulation results are given throughout the text using various intensity images.

Original languageEnglish
Pages (from-to)375-423
Number of pages49
JournalInternational Journal of Circuit Theory and Applications
Volume26
Issue number4
Publication statusPublished - Jul 1998

Fingerprint

Filter
Anisotropic Diffusion
Gaussian Noise
Diffusion Model
Template
Statistics
Robust Statistics
Grid
Analogue
Impulse Noise
Cellular neural networks
Weighted Mean
Nonlinear Filters
Adaptive Strategies
Piecewise Linear Function
Impulse noise
Adaptive Filter
Geometry
Cell
Edge Detection

Keywords

  • Adaptive non-linear filters
  • CNN Universal Machine
  • Geometry-driven diffusion
  • Non-linear cellular neural networks
  • Robust statistic filters

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

CNN-based difference-controlled adaptive non-linear image filters. / Rekeczky, Csaba; Roska, T.; Ushida, Akio.

In: International Journal of Circuit Theory and Applications, Vol. 26, No. 4, 07.1998, p. 375-423.

Research output: Contribution to journalArticle

@article{f19423335f2f4f83a2ac3b6ff3fc7286,
title = "CNN-based difference-controlled adaptive non-linear image filters",
abstract = "In this paper, we develop a common cellular neural network framework for various adaptive non-linear filters based on robust statistic and geometry-driven diffusion paradigms. The base models of both approaches are defined as difference-controlled non-linear CNN templates, while the self-adjusting property is ensured by simple analogic (analog and logic) CNN algorithms. Two adaptive strategies are shown for the order statistic class. When applied to the images distorted by impulse noise both give more visually pleasing results with lower-frequency weighted mean square error than the median base model. Generalizing a variational approach we derive the constrained anisotropic diffusion, where the output of the geometry-driven diffusion model is forced to stay close to a pre-defined morphological constraint. We propose a coarse-grid CNN approach that is capable of calculating an acceptable noise-level estimate (proportional to the variance of the Gaussian noise) and controlling the fine-grid anisotropic diffusion models. A combined geometrical-statistical approach has also been developed for filtering both the impulse and additive Gaussian noise while preserving the image structure. We briefly discuss how these methods can be embedded into a more complex algorithm performing edge detection and image segmentation. The design strategies are analysed primarily from VLSI implementation point of view; therefore all non-linear cell interactions of the CNN architecture are reduced to two fundamental non-linearities, to a sigmoid type and a radial basis function. The proposed non-linear characteristics can be approximated with simple piecewise-linear functions of the voltage difference of neighbouring cells. The simplification makes it possible to convert all space-invariant non-linear templates of this study to a standard instruction set of the CNN Universal Machine, where each instruction is coded by at most a dozen analog numbers. Examples and simulation results are given throughout the text using various intensity images.",
keywords = "Adaptive non-linear filters, CNN Universal Machine, Geometry-driven diffusion, Non-linear cellular neural networks, Robust statistic filters",
author = "Csaba Rekeczky and T. Roska and Akio Ushida",
year = "1998",
month = "7",
language = "English",
volume = "26",
pages = "375--423",
journal = "International Journal of Circuit Theory and Applications",
issn = "0098-9886",
publisher = "John Wiley and Sons Ltd",
number = "4",

}

TY - JOUR

T1 - CNN-based difference-controlled adaptive non-linear image filters

AU - Rekeczky, Csaba

AU - Roska, T.

AU - Ushida, Akio

PY - 1998/7

Y1 - 1998/7

N2 - In this paper, we develop a common cellular neural network framework for various adaptive non-linear filters based on robust statistic and geometry-driven diffusion paradigms. The base models of both approaches are defined as difference-controlled non-linear CNN templates, while the self-adjusting property is ensured by simple analogic (analog and logic) CNN algorithms. Two adaptive strategies are shown for the order statistic class. When applied to the images distorted by impulse noise both give more visually pleasing results with lower-frequency weighted mean square error than the median base model. Generalizing a variational approach we derive the constrained anisotropic diffusion, where the output of the geometry-driven diffusion model is forced to stay close to a pre-defined morphological constraint. We propose a coarse-grid CNN approach that is capable of calculating an acceptable noise-level estimate (proportional to the variance of the Gaussian noise) and controlling the fine-grid anisotropic diffusion models. A combined geometrical-statistical approach has also been developed for filtering both the impulse and additive Gaussian noise while preserving the image structure. We briefly discuss how these methods can be embedded into a more complex algorithm performing edge detection and image segmentation. The design strategies are analysed primarily from VLSI implementation point of view; therefore all non-linear cell interactions of the CNN architecture are reduced to two fundamental non-linearities, to a sigmoid type and a radial basis function. The proposed non-linear characteristics can be approximated with simple piecewise-linear functions of the voltage difference of neighbouring cells. The simplification makes it possible to convert all space-invariant non-linear templates of this study to a standard instruction set of the CNN Universal Machine, where each instruction is coded by at most a dozen analog numbers. Examples and simulation results are given throughout the text using various intensity images.

AB - In this paper, we develop a common cellular neural network framework for various adaptive non-linear filters based on robust statistic and geometry-driven diffusion paradigms. The base models of both approaches are defined as difference-controlled non-linear CNN templates, while the self-adjusting property is ensured by simple analogic (analog and logic) CNN algorithms. Two adaptive strategies are shown for the order statistic class. When applied to the images distorted by impulse noise both give more visually pleasing results with lower-frequency weighted mean square error than the median base model. Generalizing a variational approach we derive the constrained anisotropic diffusion, where the output of the geometry-driven diffusion model is forced to stay close to a pre-defined morphological constraint. We propose a coarse-grid CNN approach that is capable of calculating an acceptable noise-level estimate (proportional to the variance of the Gaussian noise) and controlling the fine-grid anisotropic diffusion models. A combined geometrical-statistical approach has also been developed for filtering both the impulse and additive Gaussian noise while preserving the image structure. We briefly discuss how these methods can be embedded into a more complex algorithm performing edge detection and image segmentation. The design strategies are analysed primarily from VLSI implementation point of view; therefore all non-linear cell interactions of the CNN architecture are reduced to two fundamental non-linearities, to a sigmoid type and a radial basis function. The proposed non-linear characteristics can be approximated with simple piecewise-linear functions of the voltage difference of neighbouring cells. The simplification makes it possible to convert all space-invariant non-linear templates of this study to a standard instruction set of the CNN Universal Machine, where each instruction is coded by at most a dozen analog numbers. Examples and simulation results are given throughout the text using various intensity images.

KW - Adaptive non-linear filters

KW - CNN Universal Machine

KW - Geometry-driven diffusion

KW - Non-linear cellular neural networks

KW - Robust statistic filters

UR - http://www.scopus.com/inward/record.url?scp=0032116248&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032116248&partnerID=8YFLogxK

M3 - Article

VL - 26

SP - 375

EP - 423

JO - International Journal of Circuit Theory and Applications

JF - International Journal of Circuit Theory and Applications

SN - 0098-9886

IS - 4

ER -