Publication result detail

Evolution of Approximate Functions for Image Thresholding

BIDLO, M.

Original Title

Evolution of Approximate Functions for Image Thresholding

English Title

Evolution of Approximate Functions for Image Thresholding

Type

Paper in proceedings (conference paper)

Original 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.

English 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.

Keywords

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

Key words in English

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

Authors

BIDLO, M.

RIV year

2023

Released

28.06.2021

Publisher

IEEE Computer Society

Location

Los Alamos

ISBN

978-1-7281-9048-8

Book

IEEE Symposium Series on Computational Intelligence (IEEE SSCI)

Pages from

1

Pages to

6

Pages count

6

URL

https://ieeexplore.ieee.org/document/9659876

BibTex

@inproceedings{BUT182262,
  author="Michal {Bidlo}",
  title="Evolution of Approximate Functions for Image Thresholding",
  booktitle="IEEE Symposium Series on Computational Intelligence (IEEE SSCI)",
  year="2021",
  pages="1--6",
  publisher="IEEE Computer Society",
  address="Los Alamos",
  doi="10.1109/SSCI50451.2021.9659876",
  isbn="978-1-7281-9048-8",
  url="https://ieeexplore.ieee.org/document/9659876"
}