Abstract

In this paper we present high sample rate array architectures, stack filter-based architectures and sorting network-based architectures for computing recursive median filters. We first develop non-pipelined architectures with lower sample periods than existing architectures, and then reduce the sample period further by pipelining. Pipelining is achieved by developing new recursive algorithms which have additional delays in the feedback paths, and using the delays as pipeline latches. We show that for 2 levels of pipelining, the sample period of the array and stack filter-based architectures reduces by a factor of 2; the sample period does not however reduce proportionately for higher levels of pipelining because of the large implementation overhead. The sample period of sorting network-based architectures, on the other hand, can be reduced to any level for MSB-first implementations.

Original languageEnglish (US)
Title of host publicationProceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing
Place of PublicationPiscataway, NJ, United States
PublisherPubl by IEEE
Volume1
ISBN (Print)0780309464
StatePublished - 1993
Event1993 IEEE International Conference on Acoustics, Speech and Signal Processing - Minneapolis, MN, USA
Duration: Apr 27 1993Apr 30 1993

Other

Other1993 IEEE International Conference on Acoustics, Speech and Signal Processing
CityMinneapolis, MN, USA
Period4/27/934/30/93

Fingerprint

Median filters
very large scale integration
Sorting
filters
Pipelines
Feedback
classifying
latches

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Acoustics and Ultrasonics

Cite this

Chakrabarti, C. (1993). VLSI architectures for recursive median filters. In Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing (Vol. 1). Piscataway, NJ, United States: Publ by IEEE.

VLSI architectures for recursive median filters. / Chakrabarti, Chaitali.

Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing. Vol. 1 Piscataway, NJ, United States : Publ by IEEE, 1993.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chakrabarti, C 1993, VLSI architectures for recursive median filters. in Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing. vol. 1, Publ by IEEE, Piscataway, NJ, United States, 1993 IEEE International Conference on Acoustics, Speech and Signal Processing, Minneapolis, MN, USA, 4/27/93.
Chakrabarti C. VLSI architectures for recursive median filters. In Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing. Vol. 1. Piscataway, NJ, United States: Publ by IEEE. 1993
Chakrabarti, Chaitali. / VLSI architectures for recursive median filters. Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing. Vol. 1 Piscataway, NJ, United States : Publ by IEEE, 1993.
@inproceedings{24943e4bd2dc4570872d7d55c8bf1220,
title = "VLSI architectures for recursive median filters",
abstract = "In this paper we present high sample rate array architectures, stack filter-based architectures and sorting network-based architectures for computing recursive median filters. We first develop non-pipelined architectures with lower sample periods than existing architectures, and then reduce the sample period further by pipelining. Pipelining is achieved by developing new recursive algorithms which have additional delays in the feedback paths, and using the delays as pipeline latches. We show that for 2 levels of pipelining, the sample period of the array and stack filter-based architectures reduces by a factor of 2; the sample period does not however reduce proportionately for higher levels of pipelining because of the large implementation overhead. The sample period of sorting network-based architectures, on the other hand, can be reduced to any level for MSB-first implementations.",
author = "Chaitali Chakrabarti",
year = "1993",
language = "English (US)",
isbn = "0780309464",
volume = "1",
booktitle = "Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - VLSI architectures for recursive median filters

AU - Chakrabarti, Chaitali

PY - 1993

Y1 - 1993

N2 - In this paper we present high sample rate array architectures, stack filter-based architectures and sorting network-based architectures for computing recursive median filters. We first develop non-pipelined architectures with lower sample periods than existing architectures, and then reduce the sample period further by pipelining. Pipelining is achieved by developing new recursive algorithms which have additional delays in the feedback paths, and using the delays as pipeline latches. We show that for 2 levels of pipelining, the sample period of the array and stack filter-based architectures reduces by a factor of 2; the sample period does not however reduce proportionately for higher levels of pipelining because of the large implementation overhead. The sample period of sorting network-based architectures, on the other hand, can be reduced to any level for MSB-first implementations.

AB - In this paper we present high sample rate array architectures, stack filter-based architectures and sorting network-based architectures for computing recursive median filters. We first develop non-pipelined architectures with lower sample periods than existing architectures, and then reduce the sample period further by pipelining. Pipelining is achieved by developing new recursive algorithms which have additional delays in the feedback paths, and using the delays as pipeline latches. We show that for 2 levels of pipelining, the sample period of the array and stack filter-based architectures reduces by a factor of 2; the sample period does not however reduce proportionately for higher levels of pipelining because of the large implementation overhead. The sample period of sorting network-based architectures, on the other hand, can be reduced to any level for MSB-first implementations.

UR - http://www.scopus.com/inward/record.url?scp=0027210192&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027210192&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0780309464

VL - 1

BT - Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

PB - Publ by IEEE

CY - Piscataway, NJ, United States

ER -