Deformation invariant image matching based on dissimilarity of spatial features

S. M M Kahaki, Md. Jan Nordin, Amir H. Ashtari, Sophia J. Zahra

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

In this paper, a new deformation invariant image matching method, known as spatial orientation feature matching (SOFM), is presented. A new similarity value, which measures the similarity of the signal through the path based on triple-wise signal eigenvector correlation, is proposed. The proposed method extracts similarity feature values by relying on the distinct path between two specific interest points and following the alternation of the signal while traversing the path. Because these similarity values of the path are deformation invariant, the proposed method supports various types of transformation in the original image, such as scale, translation, rotation, intensity noises and occlusion. Moreover, the triple-wise similarity scores are accumulated in a 2-D similarity space; thus, robust matched correspondence points are obtained using cumulative similarity space. SOFM was compared to the most recent related methods using corner correspondence (CC) and precision-recall evaluation metrics. The findings confirmed that SOFM provides higher correspondence ratios, and the results indicate that it outperforms currently utilized methods in terms of accuracy and generalization.

Original languageEnglish
JournalNeurocomputing
DOIs
Publication statusAccepted/In press - 21 Oct 2014

Fingerprint

Image matching
Eigenvalues and eigenfunctions
Noise

Keywords

  • Image formation theory
  • Image matching
  • Image registration

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Cognitive Neuroscience

Cite this

Deformation invariant image matching based on dissimilarity of spatial features. / Kahaki, S. M M; Nordin, Md. Jan; Ashtari, Amir H.; Zahra, Sophia J.

In: Neurocomputing, 21.10.2014.

Research output: Contribution to journalArticle

@article{4c8d38731755485b9eaac6ee908ef017,
title = "Deformation invariant image matching based on dissimilarity of spatial features",
abstract = "In this paper, a new deformation invariant image matching method, known as spatial orientation feature matching (SOFM), is presented. A new similarity value, which measures the similarity of the signal through the path based on triple-wise signal eigenvector correlation, is proposed. The proposed method extracts similarity feature values by relying on the distinct path between two specific interest points and following the alternation of the signal while traversing the path. Because these similarity values of the path are deformation invariant, the proposed method supports various types of transformation in the original image, such as scale, translation, rotation, intensity noises and occlusion. Moreover, the triple-wise similarity scores are accumulated in a 2-D similarity space; thus, robust matched correspondence points are obtained using cumulative similarity space. SOFM was compared to the most recent related methods using corner correspondence (CC) and precision-recall evaluation metrics. The findings confirmed that SOFM provides higher correspondence ratios, and the results indicate that it outperforms currently utilized methods in terms of accuracy and generalization.",
keywords = "Image formation theory, Image matching, Image registration",
author = "Kahaki, {S. M M} and Nordin, {Md. Jan} and Ashtari, {Amir H.} and Zahra, {Sophia J.}",
year = "2014",
month = "10",
day = "21",
doi = "10.1016/j.neucom.2015.09.106",
language = "English",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",

}

TY - JOUR

T1 - Deformation invariant image matching based on dissimilarity of spatial features

AU - Kahaki, S. M M

AU - Nordin, Md. Jan

AU - Ashtari, Amir H.

AU - Zahra, Sophia J.

PY - 2014/10/21

Y1 - 2014/10/21

N2 - In this paper, a new deformation invariant image matching method, known as spatial orientation feature matching (SOFM), is presented. A new similarity value, which measures the similarity of the signal through the path based on triple-wise signal eigenvector correlation, is proposed. The proposed method extracts similarity feature values by relying on the distinct path between two specific interest points and following the alternation of the signal while traversing the path. Because these similarity values of the path are deformation invariant, the proposed method supports various types of transformation in the original image, such as scale, translation, rotation, intensity noises and occlusion. Moreover, the triple-wise similarity scores are accumulated in a 2-D similarity space; thus, robust matched correspondence points are obtained using cumulative similarity space. SOFM was compared to the most recent related methods using corner correspondence (CC) and precision-recall evaluation metrics. The findings confirmed that SOFM provides higher correspondence ratios, and the results indicate that it outperforms currently utilized methods in terms of accuracy and generalization.

AB - In this paper, a new deformation invariant image matching method, known as spatial orientation feature matching (SOFM), is presented. A new similarity value, which measures the similarity of the signal through the path based on triple-wise signal eigenvector correlation, is proposed. The proposed method extracts similarity feature values by relying on the distinct path between two specific interest points and following the alternation of the signal while traversing the path. Because these similarity values of the path are deformation invariant, the proposed method supports various types of transformation in the original image, such as scale, translation, rotation, intensity noises and occlusion. Moreover, the triple-wise similarity scores are accumulated in a 2-D similarity space; thus, robust matched correspondence points are obtained using cumulative similarity space. SOFM was compared to the most recent related methods using corner correspondence (CC) and precision-recall evaluation metrics. The findings confirmed that SOFM provides higher correspondence ratios, and the results indicate that it outperforms currently utilized methods in terms of accuracy and generalization.

KW - Image formation theory

KW - Image matching

KW - Image registration

UR - http://www.scopus.com/inward/record.url?scp=84949009379&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949009379&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2015.09.106

DO - 10.1016/j.neucom.2015.09.106

M3 - Article

AN - SCOPUS:84949009379

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -