Detail publikace

An Area-Efficient Alternative to Adaptive Median Filtering in FPGAs

VAŠÍČEK, Z. SEKANINA, L.

Originální název

An Area-Efficient Alternative to Adaptive Median Filtering in FPGAs

Anglický název

An Area-Efficient Alternative to Adaptive Median Filtering in FPGAs

Jazyk

en

Originální abstrakt

This paper presents a new approach to the FPGA implementation of image filters which are utilized to remove the salt-and-pepper noise of high intensity (up to 70% of corrupted pixels). The proposed solution combines image filters designed by means of evolutionary algorithm with a simple human-designed preprocessing and post-processing unit. It provides the same filtering capability as a standard adaptive median filter; however, using four times less Virtex slices.

Anglický abstrakt

This paper presents a new approach to the FPGA implementation of image filters which are utilized to remove the salt-and-pepper noise of high intensity (up to 70% of corrupted pixels). The proposed solution combines image filters designed by means of evolutionary algorithm with a simple human-designed preprocessing and post-processing unit. It provides the same filtering capability as a standard adaptive median filter; however, using four times less Virtex slices.

Dokumenty

BibTex


@inproceedings{BUT28818,
  author="Zdeněk {Vašíček} and Lukáš {Sekanina}",
  title="An Area-Efficient Alternative to Adaptive Median Filtering in FPGAs",
  annote="This paper presents a new approach to the FPGA implementation of image filters
which are utilized to remove the salt-and-pepper noise of high intensity (up to
70% of corrupted pixels). The proposed solution combines image filters designed
by means of evolutionary algorithm with a simple human-designed preprocessing and
post-processing unit. It provides the same filtering capability as a standard
adaptive median filter; however, using four times less Virtex slices.
",
  address="IEEE Computer Society",
  booktitle="Proc. of 2007 International Conference on Field Programmable Logic and Applications",
  chapter="28818",
  howpublished="print",
  institution="IEEE Computer Society",
  year="2007",
  month="august",
  pages="216--221",
  publisher="IEEE Computer Society",
  type="conference paper"
}