2D Feature Detection via Local Energy

B. Robbins, Robyn Owens

Research output: Contribution to journalArticle

58 Citations (Scopus)

Abstract

Accurate detection and localisation of two-dimensional (2D) image features (or 'key-points') is important for vision tasks such as structure from motion, stereo matching and line labelling. Despite this interest, no one has produced an adequate definition of 2D image features that encompasses the variety of features that should be included under this banner. In this paper, we present a new method for the detection of 2D image features that relies upon maximal 2D order in the phase domain of the image signal. Points of maximal phase congruency correspond to all the different types of 2D features detected by other schemes, including grey-level corners, line terminations, and a variety of junctions. An assessment of our implementation's performance is provided, in terms of its robustness, accuracy of detection and localisation of 2D image features.
Original languageEnglish
Pages (from-to)353-368
JournalImage and Vision Computing
Volume15
DOIs
Publication statusPublished - 1997

Fingerprint

Labeling

Cite this

@article{aabd6b5593f24f028c60c839ede08b08,
title = "2D Feature Detection via Local Energy",
abstract = "Accurate detection and localisation of two-dimensional (2D) image features (or 'key-points') is important for vision tasks such as structure from motion, stereo matching and line labelling. Despite this interest, no one has produced an adequate definition of 2D image features that encompasses the variety of features that should be included under this banner. In this paper, we present a new method for the detection of 2D image features that relies upon maximal 2D order in the phase domain of the image signal. Points of maximal phase congruency correspond to all the different types of 2D features detected by other schemes, including grey-level corners, line terminations, and a variety of junctions. An assessment of our implementation's performance is provided, in terms of its robustness, accuracy of detection and localisation of 2D image features.",
author = "B. Robbins and Robyn Owens",
year = "1997",
doi = "10.1016/S0262-8856(96)01137-7",
language = "English",
volume = "15",
pages = "353--368",
journal = "Image and Vision Computing Journal",
issn = "0262-8856",
publisher = "Elsevier",

}

2D Feature Detection via Local Energy. / Robbins, B.; Owens, Robyn.

In: Image and Vision Computing, Vol. 15, 1997, p. 353-368.

Research output: Contribution to journalArticle

TY - JOUR

T1 - 2D Feature Detection via Local Energy

AU - Robbins, B.

AU - Owens, Robyn

PY - 1997

Y1 - 1997

N2 - Accurate detection and localisation of two-dimensional (2D) image features (or 'key-points') is important for vision tasks such as structure from motion, stereo matching and line labelling. Despite this interest, no one has produced an adequate definition of 2D image features that encompasses the variety of features that should be included under this banner. In this paper, we present a new method for the detection of 2D image features that relies upon maximal 2D order in the phase domain of the image signal. Points of maximal phase congruency correspond to all the different types of 2D features detected by other schemes, including grey-level corners, line terminations, and a variety of junctions. An assessment of our implementation's performance is provided, in terms of its robustness, accuracy of detection and localisation of 2D image features.

AB - Accurate detection and localisation of two-dimensional (2D) image features (or 'key-points') is important for vision tasks such as structure from motion, stereo matching and line labelling. Despite this interest, no one has produced an adequate definition of 2D image features that encompasses the variety of features that should be included under this banner. In this paper, we present a new method for the detection of 2D image features that relies upon maximal 2D order in the phase domain of the image signal. Points of maximal phase congruency correspond to all the different types of 2D features detected by other schemes, including grey-level corners, line terminations, and a variety of junctions. An assessment of our implementation's performance is provided, in terms of its robustness, accuracy of detection and localisation of 2D image features.

U2 - 10.1016/S0262-8856(96)01137-7

DO - 10.1016/S0262-8856(96)01137-7

M3 - Article

VL - 15

SP - 353

EP - 368

JO - Image and Vision Computing Journal

JF - Image and Vision Computing Journal

SN - 0262-8856

ER -