Publication Details

Evolution of Approximate Functions for Image Thresholding

BIDLO Michal. Evolution of Approximate Functions for Image Thresholding. In: IEEE Symposium Series on Computational Intelligence (IEEE SSCI). Los Alamos: IEEE Computer Society, 2021, pp. 1-6. ISBN 978-1-7281-9048-8. Available from: https://ieeexplore.ieee.org/document/9659876
Czech title
Evoluce přibližných algoritmů pro prahování obrazu
Type
conference paper
Language
english
Authors
Bidlo Michal, doc. Ing., Ph.D. (DCSY FIT BUT)
URL
Keywords

evolution strategy, cartesian genetic programming, approximate circuit, image thresholding

Abstract

This paper investigates the utilisation of approximate addition and multiplication for designing image thresholding functions. Cartesian Genetic Programming is applied for the evolutionary design of circuits using various implementations of the approximate operations. The results are presented for various experimental setups and compared with the case when only exact addition and multiplication is considered. It will be shown that for some range of error metrics of the approximate operations the evolution provides solutions that are better than those provided by the exact operations. Moreover, the utilisation of approximate components allows reducing the implementation area of the resulting functions.

Published
2021
Pages
1-6
Proceedings
IEEE Symposium Series on Computational Intelligence (IEEE SSCI)
Conference
IEEE Symposium Series on Computational Intelligence 2021, Orlando, US
ISBN
978-1-7281-9048-8
Publisher
IEEE Computer Society
Place
Los Alamos, US
DOI
10.1109/SSCI50451.2021.9659876
UT WoS
000824464300057
EID Scopus
2-s2.0-85125795817
BibTeX 
@INPROCEEDINGS{FITPUB12461,
   author = "Michal Bidlo",
   title = "Evolution of Approximate Functions for Image Thresholding",
   pages = "1--6",
   booktitle = "IEEE Symposium Series on Computational Intelligence (IEEE SSCI)",
   year = 2021,
   location = "Los Alamos, US",
   publisher = "IEEE Computer Society",
   ISBN = "978-1-7281-9048-8",
   doi = "10.1109/SSCI50451.2021.9659876",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12461"
}
Back to top