Publication detail

Accelerating FPGA-based evolution of wavelet transform filters by optimized task scheduling

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

Original Title

Accelerating FPGA-based evolution of wavelet transform filters by optimized task scheduling

Type

journal article in Web of Science

Language

English

Original Abstract

Adaptive embedded systems are required in various applications. This work addresses these needs in the area of adaptive image compression in FPGA devices. A simplified version of an evolution strategy is utilized to optimize wavelet filters of a Discrete Wavelet Transform algorithm. We propose an adaptive image compression system in FPGA where optimized memory architecture, parallel processing and optimized task scheduling allow reducing the time of evolution. The proposed solution has been extensively evaluated in terms of the quality of compression as well as the processing time. The proposed architecture reduces the time of evolution by 44% compared to our previous reports while maintaining the quality of compression unchanged with respect to existing implementations. The system is able to find an optimized set of wavelet filters in less than 2 min whenever the input type of data changes.

Keywords

Evolvable hardware, FPGA, Bio-inspired architectures, Adaptive embedded systems, Adaptive image compression, Evolutionary Computation, Evolved wavelet transforms, Filter optimization

Authors

SALVADOR, R.; VIDAL, A.; MORENO, F.; RIESGO, T.; SEKANINA, L.

RIV year

2012

Released

22. 6. 2012

ISBN

0141-9331

Periodical

Microprocessors and Microsystems

Year of study

36

Number

5

State

Kingdom of the Netherlands

Pages from

427

Pages to

438

Pages count

12

URL

http://www.sciencedirect.com/science/article/pii/S0141933112000191

BibTex

@article{BUT96948,
  author="Ruben {Salvador} and Alberto {Vidal} and Felix {Moreno} and Teresa {Riesgo} and Lukáš {Sekanina}",
  title="Accelerating FPGA-based evolution of wavelet transform filters by optimized task scheduling",
  journal="Microprocessors and Microsystems",
  year="2012",
  volume="36",
  number="5",
  pages="427--438",
  doi="10.1016/j.micpro.2012.02.002",
  issn="0141-9331",
  url="http://www.sciencedirect.com/science/article/pii/S0141933112000191"
}