Affine versus projective transformation for SIFT and RANSAC image matching methods

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

3 Citations (Scopus)

Abstract

Image registration is a process of determining the geometrical transformation that aligns two or more images taken from different viewpoints and sensors at different times. Scale Invariant Feature Transform (SIFT) method has gained more popularity since it extracts the highest number of features and matching points compared to Speeded-Up Robust Feature (SURF) and Harris Corner Detector at little computational cost. In this paper, a combination of SIFT and Random Sample Consensus (RANSAC) is used to produce panoramic image. In order to reject outliers and estimate the transformation model, affine and projective transformations are used to study the best geometrical transformations methods to be used. The results shows that the projective transformation has a better performance in terms of accuracy.

Original languageEnglish
Title of host publicationIEEE 2015 International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages447-451
Number of pages5
ISBN (Electronic)9781479989966
DOIs
Publication statusPublished - 17 Feb 2016
Event4th IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Kuala Lumpur, Malaysia
Duration: 19 Oct 201521 Oct 2015

Publication series

NameIEEE 2015 International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Proceedings

Other

Other4th IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2015
CountryMalaysia
CityKuala Lumpur
Period19/10/1521/10/15

Fingerprint

Image matching
Mathematical transformations
Image registration
Detectors
Sensors
Costs

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Signal Processing

Cite this

Redzuwan, R., Mohamed Radzi, N. A., Md Din, N., & Mustafa, I. S. (2016). Affine versus projective transformation for SIFT and RANSAC image matching methods. In IEEE 2015 International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Proceedings (pp. 447-451). [7412233] (IEEE 2015 International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSIPA.2015.7412233
Redzuwan, Redia ; Mohamed Radzi, Nurul Asyikin ; Md Din, Norashidah ; Mustafa, Intan Shafinaz. / Affine versus projective transformation for SIFT and RANSAC image matching methods. IEEE 2015 International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 447-451 (IEEE 2015 International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Proceedings).
@inproceedings{d5512a420e60412db830d2404fe4556d,
title = "Affine versus projective transformation for SIFT and RANSAC image matching methods",
abstract = "Image registration is a process of determining the geometrical transformation that aligns two or more images taken from different viewpoints and sensors at different times. Scale Invariant Feature Transform (SIFT) method has gained more popularity since it extracts the highest number of features and matching points compared to Speeded-Up Robust Feature (SURF) and Harris Corner Detector at little computational cost. In this paper, a combination of SIFT and Random Sample Consensus (RANSAC) is used to produce panoramic image. In order to reject outliers and estimate the transformation model, affine and projective transformations are used to study the best geometrical transformations methods to be used. The results shows that the projective transformation has a better performance in terms of accuracy.",
author = "Redia Redzuwan and {Mohamed Radzi}, {Nurul Asyikin} and {Md Din}, Norashidah and Mustafa, {Intan Shafinaz}",
year = "2016",
month = "2",
day = "17",
doi = "10.1109/ICSIPA.2015.7412233",
language = "English",
series = "IEEE 2015 International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "447--451",
booktitle = "IEEE 2015 International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Proceedings",
address = "United States",

}

Redzuwan, R, Mohamed Radzi, NA, Md Din, N & Mustafa, IS 2016, Affine versus projective transformation for SIFT and RANSAC image matching methods. in IEEE 2015 International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Proceedings., 7412233, IEEE 2015 International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 447-451, 4th IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2015, Kuala Lumpur, Malaysia, 19/10/15. https://doi.org/10.1109/ICSIPA.2015.7412233

Affine versus projective transformation for SIFT and RANSAC image matching methods. / Redzuwan, Redia; Mohamed Radzi, Nurul Asyikin; Md Din, Norashidah; Mustafa, Intan Shafinaz.

IEEE 2015 International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. p. 447-451 7412233 (IEEE 2015 International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Proceedings).

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

TY - GEN

T1 - Affine versus projective transformation for SIFT and RANSAC image matching methods

AU - Redzuwan, Redia

AU - Mohamed Radzi, Nurul Asyikin

AU - Md Din, Norashidah

AU - Mustafa, Intan Shafinaz

PY - 2016/2/17

Y1 - 2016/2/17

N2 - Image registration is a process of determining the geometrical transformation that aligns two or more images taken from different viewpoints and sensors at different times. Scale Invariant Feature Transform (SIFT) method has gained more popularity since it extracts the highest number of features and matching points compared to Speeded-Up Robust Feature (SURF) and Harris Corner Detector at little computational cost. In this paper, a combination of SIFT and Random Sample Consensus (RANSAC) is used to produce panoramic image. In order to reject outliers and estimate the transformation model, affine and projective transformations are used to study the best geometrical transformations methods to be used. The results shows that the projective transformation has a better performance in terms of accuracy.

AB - Image registration is a process of determining the geometrical transformation that aligns two or more images taken from different viewpoints and sensors at different times. Scale Invariant Feature Transform (SIFT) method has gained more popularity since it extracts the highest number of features and matching points compared to Speeded-Up Robust Feature (SURF) and Harris Corner Detector at little computational cost. In this paper, a combination of SIFT and Random Sample Consensus (RANSAC) is used to produce panoramic image. In order to reject outliers and estimate the transformation model, affine and projective transformations are used to study the best geometrical transformations methods to be used. The results shows that the projective transformation has a better performance in terms of accuracy.

UR - http://www.scopus.com/inward/record.url?scp=84971643944&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84971643944&partnerID=8YFLogxK

U2 - 10.1109/ICSIPA.2015.7412233

DO - 10.1109/ICSIPA.2015.7412233

M3 - Conference contribution

T3 - IEEE 2015 International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Proceedings

SP - 447

EP - 451

BT - IEEE 2015 International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Redzuwan R, Mohamed Radzi NA, Md Din N, Mustafa IS. Affine versus projective transformation for SIFT and RANSAC image matching methods. In IEEE 2015 International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2016. p. 447-451. 7412233. (IEEE 2015 International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Proceedings). https://doi.org/10.1109/ICSIPA.2015.7412233