Sieves and wavelets: multiscale transforms for pattern recognition

JA Bangham; TG Campbell

doi:10.1109/NDSP.1993.767679

Sieves and wavelets: multiscale transforms for pattern recognition

JA Bangham, TG Campbell

School of Computing Sciences

Research output: Contribution to conference › Other

Abstract

In this paper a scalelposition decomposition that is an alternative to wavelets is described. The nonlinear decomposition, called the datasieve, is appropriate for isolating and locating the position of objects with sharp edges arising from nonlinear events such as occlusion. It can represent structural information in a way that is independent of spatial frequency, has different uncertainty tradeoffs, and can be used for scale, position and contrast independent pattern recognition.

Original language	English
Pages	1.1_4.1-1.1_4.6
Number of pages	6
DOIs	https://doi.org/10.1109/NDSP.1993.767679
Publication status	Published - 1993
Event	IEEE Winter Workshop on Nonlinear Digital Signal Processing - Duration: 17 Jan 1993 → 20 Jan 1993

Conference

Conference	IEEE Winter Workshop on Nonlinear Digital Signal Processing
Period	17/01/93 → 20/01/93

Access to Document

10.1109/NDSP.1993.767679

Cite this

@conference{a9f1d3678f1a4c98aa5bab831ca08439,

title = "Sieves and wavelets: multiscale transforms for pattern recognition",

abstract = "In this paper a scalelposition decomposition that is an alternative to wavelets is described. The nonlinear decomposition, called the datasieve, is appropriate for isolating and locating the position of objects with sharp edges arising from nonlinear events such as occlusion. It can represent structural information in a way that is independent of spatial frequency, has different uncertainty tradeoffs, and can be used for scale, position and contrast independent pattern recognition.",

author = "JA Bangham and TG Campbell",

year = "1993",

doi = "10.1109/NDSP.1993.767679",

language = "English",

pages = "1.1_4.1--1.1_4.6",

note = "IEEE Winter Workshop on Nonlinear Digital Signal Processing ; Conference date: 17-01-1993 Through 20-01-1993",

}

TY - CONF

T1 - Sieves and wavelets: multiscale transforms for pattern recognition

AU - Bangham, JA

AU - Campbell, TG

PY - 1993

Y1 - 1993

N2 - In this paper a scalelposition decomposition that is an alternative to wavelets is described. The nonlinear decomposition, called the datasieve, is appropriate for isolating and locating the position of objects with sharp edges arising from nonlinear events such as occlusion. It can represent structural information in a way that is independent of spatial frequency, has different uncertainty tradeoffs, and can be used for scale, position and contrast independent pattern recognition.

AB - In this paper a scalelposition decomposition that is an alternative to wavelets is described. The nonlinear decomposition, called the datasieve, is appropriate for isolating and locating the position of objects with sharp edges arising from nonlinear events such as occlusion. It can represent structural information in a way that is independent of spatial frequency, has different uncertainty tradeoffs, and can be used for scale, position and contrast independent pattern recognition.

U2 - 10.1109/NDSP.1993.767679

DO - 10.1109/NDSP.1993.767679

M3 - Other

SP - 1.1_4.1-1.1_4.6

T2 - IEEE Winter Workshop on Nonlinear Digital Signal Processing

Y2 - 17 January 1993 through 20 January 1993

ER -