Publication detail

Evolutionary Approach to Improve Wavelet Transforms for Image Compression in Embedded Systems

SALVADOR, R. MORENO, F. RIESGO, T. SEKANINA, L.

Original Title

Evolutionary Approach to Improve Wavelet Transforms for Image Compression in Embedded Systems

English Title

Evolutionary Approach to Improve Wavelet Transforms for Image Compression in Embedded Systems

Type

journal article - other

Language

en

Original Abstract

A bioinspired, evolutionary algorithm for optimizing wavelet transforms oriented to improve image compression in embedded systems is proposed, modelled, and validated here. A simplified version of an Evolution Strategy, using fixed point arithmetic and a hardware-friendly mutation operator, has been chosen as the search algorithm. Several cutdowns on the computing requirements have been done to the original algorithm, adapting it for an FPGA implementation. The work presented in this paper describes the algorithm as well as the test strategy developed to validate it, showing several results in the effort to find a suitable set of parameters that assure the success in the evolutionary search. The results show how high-quality transforms are evolved from scratch with limited precision arithmetic and a simplified algorithm. Since the intended deployment platform is an FPGA, HW/SW partitioning issues are also considered as well as code profiling accomplished to validate the proposal, showing some preliminary results of the proposed hardware architecture.

English abstract

A bioinspired, evolutionary algorithm for optimizing wavelet transforms oriented to improve image compression in embedded systems is proposed, modelled, and validated here. A simplified version of an Evolution Strategy, using fixed point arithmetic and a hardware-friendly mutation operator, has been chosen as the search algorithm. Several cutdowns on the computing requirements have been done to the original algorithm, adapting it for an FPGA implementation. The work presented in this paper describes the algorithm as well as the test strategy developed to validate it, showing several results in the effort to find a suitable set of parameters that assure the success in the evolutionary search. The results show how high-quality transforms are evolved from scratch with limited precision arithmetic and a simplified algorithm. Since the intended deployment platform is an FPGA, HW/SW partitioning issues are also considered as well as code profiling accomplished to validate the proposal, showing some preliminary results of the proposed hardware architecture.

Keywords

evolution strategy, wavelet transform, FPGA, image compression

RIV year

2011

Released

17.02.2011

Publisher

NEUVEDEN

Location

NEUVEDEN

Pages from

1

Pages to

20

Pages count

20

URL

Documents

BibTex


@article{BUT76274,
  author="Ruben {Salvador} and Felix {Moreno} and Teresa {Riesgo} and Lukáš {Sekanina}",
  title="Evolutionary Approach to Improve Wavelet Transforms for Image Compression in Embedded Systems",
  annote="A bioinspired, evolutionary algorithm for optimizing wavelet transforms oriented
to improve image compression in embedded systems is proposed, modelled, and
validated here. A simplified version of an Evolution Strategy, using fixed point
arithmetic and a hardware-friendly mutation operator, has been chosen as the
search algorithm. Several cutdowns on the computing requirements have been done
to the original algorithm, adapting it for an FPGA implementation. The work
presented in this paper describes the algorithm as well as the test strategy
developed to validate it, showing several results in the effort to find
a suitable set of parameters that assure the success in the evolutionary search.
The results show how high-quality transforms are evolved from scratch with
limited precision arithmetic and a simplified algorithm. Since the intended
deployment platform is an FPGA, HW/SW partitioning issues are also considered as
well as code profiling accomplished to validate the proposal, showing some
preliminary results of the proposed hardware architecture.",
  address="NEUVEDEN",
  chapter="76274",
  edition="NEUVEDEN",
  howpublished="print",
  institution="NEUVEDEN",
  number="2011",
  volume="2011",
  year="2011",
  month="february",
  pages="1--20",
  publisher="NEUVEDEN",
  type="journal article - other"
}