Subband coding and image compression using CNN

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

The cellular neural network paradigm has found many applications in image processing. However, algorithms for image compression using CNN have scarcely been explored. CNN programmability is based on a new algorithmic style based on the spatio-temporal properties of the array. By exploiting the massive parallelism provided by CNN and the convolutional key basic instruction, a fast and efficient compression process can be achieved. This paper presents new templates and low-complexity algorithms to perform both the linear and non-linear operations needed for image compression. In this work, we have addressed all the transformation steps needed in image compression, i.e. decorrelation, bit allocation, quantization and bit extraction. From all possible compression techniques the wavelet subband coding was chosen because it is considered one of the most successful techniques for lossy compression. It allows a high compression ratio while preserving the image quality. All these advantages are implemented in the algorithms hereby presented.

Original languageEnglish
Pages (from-to)135-151
Number of pages17
JournalInternational Journal of Circuit Theory and Applications
Volume27
Issue number1
DOIs
Publication statusPublished - Jan 1999

Fingerprint

Image Compression
Image compression
Compression
Coding
Bit Allocation
Quantization (signal)
Lossy Compression
Cellular neural networks
Cellular Networks
Image Quality
Low Complexity
Image quality
Parallelism
Template
Image Processing
Quantization
Wavelets
Image processing
Paradigm
Neural Networks

Keywords

  • Cellular neural networks
  • Image compression
  • Subband coding

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Subband coding and image compression using CNN. / Zarándy, A.

In: International Journal of Circuit Theory and Applications, Vol. 27, No. 1, 01.1999, p. 135-151.

Research output: Contribution to journalArticle

@article{f3138347b35f4e0581738cbd341ed03f,
title = "Subband coding and image compression using CNN",
abstract = "The cellular neural network paradigm has found many applications in image processing. However, algorithms for image compression using CNN have scarcely been explored. CNN programmability is based on a new algorithmic style based on the spatio-temporal properties of the array. By exploiting the massive parallelism provided by CNN and the convolutional key basic instruction, a fast and efficient compression process can be achieved. This paper presents new templates and low-complexity algorithms to perform both the linear and non-linear operations needed for image compression. In this work, we have addressed all the transformation steps needed in image compression, i.e. decorrelation, bit allocation, quantization and bit extraction. From all possible compression techniques the wavelet subband coding was chosen because it is considered one of the most successful techniques for lossy compression. It allows a high compression ratio while preserving the image quality. All these advantages are implemented in the algorithms hereby presented.",
keywords = "Cellular neural networks, Image compression, Subband coding",
author = "A. Zar{\'a}ndy",
year = "1999",
month = "1",
doi = "10.1002/(SICI)1097-007X(199901/02)27:1<135::AID-CTA45>3.0.CO;2-A",
language = "English",
volume = "27",
pages = "135--151",
journal = "International Journal of Circuit Theory and Applications",
issn = "0098-9886",
publisher = "John Wiley and Sons Ltd",
number = "1",

}

TY - JOUR

T1 - Subband coding and image compression using CNN

AU - Zarándy, A.

PY - 1999/1

Y1 - 1999/1

N2 - The cellular neural network paradigm has found many applications in image processing. However, algorithms for image compression using CNN have scarcely been explored. CNN programmability is based on a new algorithmic style based on the spatio-temporal properties of the array. By exploiting the massive parallelism provided by CNN and the convolutional key basic instruction, a fast and efficient compression process can be achieved. This paper presents new templates and low-complexity algorithms to perform both the linear and non-linear operations needed for image compression. In this work, we have addressed all the transformation steps needed in image compression, i.e. decorrelation, bit allocation, quantization and bit extraction. From all possible compression techniques the wavelet subband coding was chosen because it is considered one of the most successful techniques for lossy compression. It allows a high compression ratio while preserving the image quality. All these advantages are implemented in the algorithms hereby presented.

AB - The cellular neural network paradigm has found many applications in image processing. However, algorithms for image compression using CNN have scarcely been explored. CNN programmability is based on a new algorithmic style based on the spatio-temporal properties of the array. By exploiting the massive parallelism provided by CNN and the convolutional key basic instruction, a fast and efficient compression process can be achieved. This paper presents new templates and low-complexity algorithms to perform both the linear and non-linear operations needed for image compression. In this work, we have addressed all the transformation steps needed in image compression, i.e. decorrelation, bit allocation, quantization and bit extraction. From all possible compression techniques the wavelet subband coding was chosen because it is considered one of the most successful techniques for lossy compression. It allows a high compression ratio while preserving the image quality. All these advantages are implemented in the algorithms hereby presented.

KW - Cellular neural networks

KW - Image compression

KW - Subband coding

UR - http://www.scopus.com/inward/record.url?scp=0032600090&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032600090&partnerID=8YFLogxK

U2 - 10.1002/(SICI)1097-007X(199901/02)27:1<135::AID-CTA45>3.0.CO;2-A

DO - 10.1002/(SICI)1097-007X(199901/02)27:1<135::AID-CTA45>3.0.CO;2-A

M3 - Article

AN - SCOPUS:0032600090

VL - 27

SP - 135

EP - 151

JO - International Journal of Circuit Theory and Applications

JF - International Journal of Circuit Theory and Applications

SN - 0098-9886

IS - 1

ER -