Publication Details

Evolutionary Approximation of Edge Detection Circuits

DVOŘÁČEK, P.; SEKANINA, L. Evolutionary Approximation of Edge Detection Circuits. In 19th European Conference on Genetic programming. Lecture Notes in Computer Science. Berlin: Springer International Publishing, 2016. p. 19-34. ISBN: 978-3-319-30667-4.
Czech title
Evoluční aproximace obvodů detekujících hrany
Type
conference paper
Language
English
Authors
Keywords

Edge detection circuits, Cartesian genetic programming, Evolutionary computation

Abstract


Approximate computing exploits the fact that many applications are inherently
error resilient which means that some errors in their outputs can safely be
exchanged for improving other parameters such as energy consumption or operation
frequency. A new method based on evolutionary computing is proposed in this paper
which enables to approximate edge detection circuits. Rather than evolving
approximate edge detectors from scratch, key components of existing edge detector
are replaced by their approximate versions obtained using Cartesian genetic
programming (CGP). Various approximate edge detectors are then composed and their
quality is evaluated using a database of images. The paper reports interesting
edge detectors showing a good tradeoff between the quality of edge detection and
implementation cost.

Published
2016
Pages
19–34
Proceedings
19th European Conference on Genetic programming
Series
Lecture Notes in Computer Science
Volume
9594
Conference
19th European Conference on Genetic Programming, Porto, PT
ISBN
978-3-319-30667-4
Publisher
Springer International Publishing
Place
Berlin
DOI
UT WoS
000894258400002
EID Scopus
BibTeX
@inproceedings{BUT130921,
  author="Petr {Dvořáček} and Lukáš {Sekanina}",
  title="Evolutionary Approximation of Edge Detection Circuits",
  booktitle="19th European Conference on Genetic programming",
  year="2016",
  series="Lecture Notes in Computer Science",
  volume="9594",
  pages="19--34",
  publisher="Springer International Publishing",
  address="Berlin",
  doi="10.1007/978-3-319-30668-1\{_}2",
  isbn="978-3-319-30667-4",
  url="https://www.fit.vut.cz/research/publication/10998/"
}
Files
Back to top