Improving Angular Error via Systematically Designed Near-circular Gaussian-based Feature Extraction Operators

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

In image filtering, the ‘circularity’ of an operator is an important factor affecting its accuracy. For example, circular differential edge operators are effective in minimising the angular error in the estimation of image gradient direction. We present a general approach to the computation of scalable circular low-level image processing operators that is based on the finite element method. We show that the use of Gaussian basis functions within the finite element method provides a framework for a systematic and efficient design procedure for operators that are scalable to near-circular neighbourhoods through the use of an explicit scale parameter. The general design technique may be applied to a range of operators. Here we evaluate the approach for the design of the image gradient operator. We illustrate that this design procedure significantly reduces angular error in comparison to other well-known gradient approximation methods.
LanguageEnglish
Pages1451-1465
JournalPattern Recognition
Volume40
Issue number5
DOIs
Publication statusPublished - 1 May 2007

Fingerprint

Feature extraction
Finite element method
Mathematical operators
Image processing

Keywords

  • Circularity
  • Angular error
  • Feature extraction

Cite this

@article{0db18658900440ce9528bc85d438d300,
title = "Improving Angular Error via Systematically Designed Near-circular Gaussian-based Feature Extraction Operators",
abstract = "In image filtering, the ‘circularity’ of an operator is an important factor affecting its accuracy. For example, circular differential edge operators are effective in minimising the angular error in the estimation of image gradient direction. We present a general approach to the computation of scalable circular low-level image processing operators that is based on the finite element method. We show that the use of Gaussian basis functions within the finite element method provides a framework for a systematic and efficient design procedure for operators that are scalable to near-circular neighbourhoods through the use of an explicit scale parameter. The general design technique may be applied to a range of operators. Here we evaluate the approach for the design of the image gradient operator. We illustrate that this design procedure significantly reduces angular error in comparison to other well-known gradient approximation methods.",
keywords = "Circularity, Angular error, Feature extraction",
author = "BW Scotney and SA Coleman",
note = "Other Details ------------------------------------ Early work, e.g., Davies (Image Vision Computing, 1984 and 1987), established the importance of circularity in designing feature extraction operators, but implementation typically has been restricted to small neighbourhood operators. This paper addresses the key issue of scalability by developing a general, but practical, framework to enable fully scalable circular operators to be designed and implemented efficiently. Highly accurate angular orientation results are demonstrated. The work is currently being developed in collaboration between our Information & Software Engineering and Intelligent Systems research groups for application to range image data in an EPSRC-funded project on Direct Range Image Processing (EP/C006283/1).",
year = "2007",
month = "5",
day = "1",
doi = "10.1016/j.patcog.2006.10.020",
language = "English",
volume = "40",
pages = "1451--1465",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier",
number = "5",

}

Improving Angular Error via Systematically Designed Near-circular Gaussian-based Feature Extraction Operators. / Scotney, BW; Coleman, SA.

In: Pattern Recognition, Vol. 40, No. 5, 01.05.2007, p. 1451-1465.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Improving Angular Error via Systematically Designed Near-circular Gaussian-based Feature Extraction Operators

AU - Scotney, BW

AU - Coleman, SA

N1 - Other Details ------------------------------------ Early work, e.g., Davies (Image Vision Computing, 1984 and 1987), established the importance of circularity in designing feature extraction operators, but implementation typically has been restricted to small neighbourhood operators. This paper addresses the key issue of scalability by developing a general, but practical, framework to enable fully scalable circular operators to be designed and implemented efficiently. Highly accurate angular orientation results are demonstrated. The work is currently being developed in collaboration between our Information & Software Engineering and Intelligent Systems research groups for application to range image data in an EPSRC-funded project on Direct Range Image Processing (EP/C006283/1).

PY - 2007/5/1

Y1 - 2007/5/1

N2 - In image filtering, the ‘circularity’ of an operator is an important factor affecting its accuracy. For example, circular differential edge operators are effective in minimising the angular error in the estimation of image gradient direction. We present a general approach to the computation of scalable circular low-level image processing operators that is based on the finite element method. We show that the use of Gaussian basis functions within the finite element method provides a framework for a systematic and efficient design procedure for operators that are scalable to near-circular neighbourhoods through the use of an explicit scale parameter. The general design technique may be applied to a range of operators. Here we evaluate the approach for the design of the image gradient operator. We illustrate that this design procedure significantly reduces angular error in comparison to other well-known gradient approximation methods.

AB - In image filtering, the ‘circularity’ of an operator is an important factor affecting its accuracy. For example, circular differential edge operators are effective in minimising the angular error in the estimation of image gradient direction. We present a general approach to the computation of scalable circular low-level image processing operators that is based on the finite element method. We show that the use of Gaussian basis functions within the finite element method provides a framework for a systematic and efficient design procedure for operators that are scalable to near-circular neighbourhoods through the use of an explicit scale parameter. The general design technique may be applied to a range of operators. Here we evaluate the approach for the design of the image gradient operator. We illustrate that this design procedure significantly reduces angular error in comparison to other well-known gradient approximation methods.

KW - Circularity

KW - Angular error

KW - Feature extraction

U2 - 10.1016/j.patcog.2006.10.020

DO - 10.1016/j.patcog.2006.10.020

M3 - Article

VL - 40

SP - 1451

EP - 1465

JO - Pattern Recognition

T2 - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 5

ER -