MIFT: A moment-based local feature extraction algorithm

Hua Zhen Zhang, Dong Won Kim, Tae Koo Kang, Myo Taeg Lim

Research output: Contribution to journalArticle

Abstract

We propose a local feature descriptor based on moment. Although conventional scale invariant feature transform (SIFT)-based algorithms generally use difference of Gaussian (DoG) for feature extraction, they remain sensitive to more complicated deformations. To solve this problem, we propose MIFT, an invariant feature transform algorithm based on the modified discrete Gaussian-Hermite moment (MDGHM). Taking advantage of MDGHM's high performance to represent image information, MIFT uses an MDGHM-based pyramid for feature extraction, which can extract more distinctive extrema than the DoG, and MDGHM-based magnitude and orientation for feature description. We compared the proposed MIFT method performance with current best practice methods for six image deformation types, and confirmed that MIFT matching accuracy was superior of other SIFT-based methods.

Original languageEnglish
Article number1503
JournalApplied Sciences (Switzerland)
Volume9
Issue number7
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

pattern recognition
Feature extraction
moments
Information use
range (extremes)
pyramids

Keywords

  • Feature extraction
  • MDGHM
  • SIFT

ASJC Scopus subject areas

  • Materials Science(all)
  • Instrumentation
  • Engineering(all)
  • Process Chemistry and Technology
  • Computer Science Applications
  • Fluid Flow and Transfer Processes

Cite this

MIFT : A moment-based local feature extraction algorithm. / Zhang, Hua Zhen; Kim, Dong Won; Kang, Tae Koo; Lim, Myo Taeg.

In: Applied Sciences (Switzerland), Vol. 9, No. 7, 1503, 01.01.2019.

Research output: Contribution to journalArticle

Zhang, Hua Zhen ; Kim, Dong Won ; Kang, Tae Koo ; Lim, Myo Taeg. / MIFT : A moment-based local feature extraction algorithm. In: Applied Sciences (Switzerland). 2019 ; Vol. 9, No. 7.
@article{64350beae4444af3813452af9d78124f,
title = "MIFT: A moment-based local feature extraction algorithm",
abstract = "We propose a local feature descriptor based on moment. Although conventional scale invariant feature transform (SIFT)-based algorithms generally use difference of Gaussian (DoG) for feature extraction, they remain sensitive to more complicated deformations. To solve this problem, we propose MIFT, an invariant feature transform algorithm based on the modified discrete Gaussian-Hermite moment (MDGHM). Taking advantage of MDGHM's high performance to represent image information, MIFT uses an MDGHM-based pyramid for feature extraction, which can extract more distinctive extrema than the DoG, and MDGHM-based magnitude and orientation for feature description. We compared the proposed MIFT method performance with current best practice methods for six image deformation types, and confirmed that MIFT matching accuracy was superior of other SIFT-based methods.",
keywords = "Feature extraction, MDGHM, SIFT",
author = "Zhang, {Hua Zhen} and Kim, {Dong Won} and Kang, {Tae Koo} and Lim, {Myo Taeg}",
year = "2019",
month = "1",
day = "1",
doi = "10.3390/APP9071503",
language = "English",
volume = "9",
journal = "Applied Sciences (Switzerland)",
issn = "2076-3417",
publisher = "Multidisciplinary Digital Publishing Institute",
number = "7",

}

TY - JOUR

T1 - MIFT

T2 - A moment-based local feature extraction algorithm

AU - Zhang, Hua Zhen

AU - Kim, Dong Won

AU - Kang, Tae Koo

AU - Lim, Myo Taeg

PY - 2019/1/1

Y1 - 2019/1/1

N2 - We propose a local feature descriptor based on moment. Although conventional scale invariant feature transform (SIFT)-based algorithms generally use difference of Gaussian (DoG) for feature extraction, they remain sensitive to more complicated deformations. To solve this problem, we propose MIFT, an invariant feature transform algorithm based on the modified discrete Gaussian-Hermite moment (MDGHM). Taking advantage of MDGHM's high performance to represent image information, MIFT uses an MDGHM-based pyramid for feature extraction, which can extract more distinctive extrema than the DoG, and MDGHM-based magnitude and orientation for feature description. We compared the proposed MIFT method performance with current best practice methods for six image deformation types, and confirmed that MIFT matching accuracy was superior of other SIFT-based methods.

AB - We propose a local feature descriptor based on moment. Although conventional scale invariant feature transform (SIFT)-based algorithms generally use difference of Gaussian (DoG) for feature extraction, they remain sensitive to more complicated deformations. To solve this problem, we propose MIFT, an invariant feature transform algorithm based on the modified discrete Gaussian-Hermite moment (MDGHM). Taking advantage of MDGHM's high performance to represent image information, MIFT uses an MDGHM-based pyramid for feature extraction, which can extract more distinctive extrema than the DoG, and MDGHM-based magnitude and orientation for feature description. We compared the proposed MIFT method performance with current best practice methods for six image deformation types, and confirmed that MIFT matching accuracy was superior of other SIFT-based methods.

KW - Feature extraction

KW - MDGHM

KW - SIFT

UR - http://www.scopus.com/inward/record.url?scp=85069763678&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069763678&partnerID=8YFLogxK

U2 - 10.3390/APP9071503

DO - 10.3390/APP9071503

M3 - Article

AN - SCOPUS:85069763678

VL - 9

JO - Applied Sciences (Switzerland)

JF - Applied Sciences (Switzerland)

SN - 2076-3417

IS - 7

M1 - 1503

ER -