Robust Feature Matching Using The FESID Detector

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

Abstract

Recently, interest point detectors and descriptors have become prominent in the field of computer vision and are typically used to determine correspondences between two images of the same scene. The finite element scale invariant detector (FESID) is based on a similar multi-scale approach to that used in the SURF detector. However, FESID detects point features rather than blob features, and by combining the derivative and smoothing operations into a single operator efficient performance is achieved. We illustrate the performance of the FESID algorithm with respect to both robustness and correct region matching.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages220-232
Number of pages12
Publication statusPublished - 2011
EventInternational Machine Vision and Image Processing Conference (IMVIP 2010) - Limerick, Ireland
Duration: 1 Jan 2011 → …

Conference

ConferenceInternational Machine Vision and Image Processing Conference (IMVIP 2010)
Period1/01/11 → …

Fingerprint

Detectors
Computer vision
Derivatives

Cite this

@inproceedings{c23117d39c32460ea2c59756bc21458c,
title = "Robust Feature Matching Using The FESID Detector",
abstract = "Recently, interest point detectors and descriptors have become prominent in the field of computer vision and are typically used to determine correspondences between two images of the same scene. The finite element scale invariant detector (FESID) is based on a similar multi-scale approach to that used in the SURF detector. However, FESID detects point features rather than blob features, and by combining the derivative and smoothing operations into a single operator efficient performance is achieved. We illustrate the performance of the FESID algorithm with respect to both robustness and correct region matching.",
author = "D Kerr and SA Coleman and BW Scotney",
year = "2011",
language = "English",
isbn = "1-4438-2962-5",
pages = "220--232",
booktitle = "Unknown Host Publication",

}

Kerr, D, Coleman, SA & Scotney, BW 2011, Robust Feature Matching Using The FESID Detector. in Unknown Host Publication. pp. 220-232, International Machine Vision and Image Processing Conference (IMVIP 2010), 1/01/11.

Robust Feature Matching Using The FESID Detector. / Kerr, D; Coleman, SA; Scotney, BW.

Unknown Host Publication. 2011. p. 220-232.

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

TY - GEN

T1 - Robust Feature Matching Using The FESID Detector

AU - Kerr, D

AU - Coleman, SA

AU - Scotney, BW

PY - 2011

Y1 - 2011

N2 - Recently, interest point detectors and descriptors have become prominent in the field of computer vision and are typically used to determine correspondences between two images of the same scene. The finite element scale invariant detector (FESID) is based on a similar multi-scale approach to that used in the SURF detector. However, FESID detects point features rather than blob features, and by combining the derivative and smoothing operations into a single operator efficient performance is achieved. We illustrate the performance of the FESID algorithm with respect to both robustness and correct region matching.

AB - Recently, interest point detectors and descriptors have become prominent in the field of computer vision and are typically used to determine correspondences between two images of the same scene. The finite element scale invariant detector (FESID) is based on a similar multi-scale approach to that used in the SURF detector. However, FESID detects point features rather than blob features, and by combining the derivative and smoothing operations into a single operator efficient performance is achieved. We illustrate the performance of the FESID algorithm with respect to both robustness and correct region matching.

M3 - Conference contribution

SN - 1-4438-2962-5

SP - 220

EP - 232

BT - Unknown Host Publication

ER -