Fast affine-invariant image matching based on global Bhattacharyya measure with adaptive tree

Jongin Son, Seungryong Kim, Kwanghoon Sohn

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

1 Citation (Scopus)

Abstract

Establishing visual correspondence is one of the most fundamental tasks in many applications of computer vision fields. In this paper we propose a robust image matching to address the affine variation problems between two images taken under different viewpoints. Unlike the conventional approach finding the correspondence with local feature matching on fully affine transformed-images, which provides many outliers with a time consuming scheme, our approach is to find only one global correspondence and then utilizes the local feature matching to estimate the most reliable inliers between two images. In order to estimate a global image correspondence very fast as varying affine transformation in affine space of reference and query images, we employ a Bhattacharyya similarity measure between two images. Furthermore, an adaptive tree with affine transformation model is employed to dramatically reduce the computational complexity. Our approach represents the satisfactory results for severe affine transformed-images while providing a very low computational time. Experimental results show that the proposed affine-invariant image matching is twice faster than the state-of-the-art methods at least, and provides better correspondence performance under viewpoint change conditions.

Original languageEnglish
Title of host publication2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings
PublisherIEEE Computer Society
Pages3190-3194
Number of pages5
Volume2015-December
ISBN (Electronic)9781479983391
DOIs
Publication statusPublished - 2015 Dec 9
EventIEEE International Conference on Image Processing, ICIP 2015 - Quebec City, Canada
Duration: 2015 Sep 272015 Sep 30

Other

OtherIEEE International Conference on Image Processing, ICIP 2015
CountryCanada
CityQuebec City
Period15/9/2715/9/30

Fingerprint

Image matching
Computer vision
Computational complexity

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Son, J., Kim, S., & Sohn, K. (2015). Fast affine-invariant image matching based on global Bhattacharyya measure with adaptive tree. In 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings (Vol. 2015-December, pp. 3190-3194). [7351392] IEEE Computer Society. https://doi.org/10.1109/ICIP.2015.7351392
Son, Jongin ; Kim, Seungryong ; Sohn, Kwanghoon. / Fast affine-invariant image matching based on global Bhattacharyya measure with adaptive tree. 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings. Vol. 2015-December IEEE Computer Society, 2015. pp. 3190-3194
@inproceedings{696e98cabcfe42e9a2a3b5a3969aad9f,
title = "Fast affine-invariant image matching based on global Bhattacharyya measure with adaptive tree",
abstract = "Establishing visual correspondence is one of the most fundamental tasks in many applications of computer vision fields. In this paper we propose a robust image matching to address the affine variation problems between two images taken under different viewpoints. Unlike the conventional approach finding the correspondence with local feature matching on fully affine transformed-images, which provides many outliers with a time consuming scheme, our approach is to find only one global correspondence and then utilizes the local feature matching to estimate the most reliable inliers between two images. In order to estimate a global image correspondence very fast as varying affine transformation in affine space of reference and query images, we employ a Bhattacharyya similarity measure between two images. Furthermore, an adaptive tree with affine transformation model is employed to dramatically reduce the computational complexity. Our approach represents the satisfactory results for severe affine transformed-images while providing a very low computational time. Experimental results show that the proposed affine-invariant image matching is twice faster than the state-of-the-art methods at least, and provides better correspondence performance under viewpoint change conditions.",
author = "Jongin Son and Seungryong Kim and Kwanghoon Sohn",
year = "2015",
month = "12",
day = "9",
doi = "10.1109/ICIP.2015.7351392",
language = "English",
volume = "2015-December",
pages = "3190--3194",
booktitle = "2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings",
publisher = "IEEE Computer Society",
address = "United States",

}

Son, J, Kim, S & Sohn, K 2015, Fast affine-invariant image matching based on global Bhattacharyya measure with adaptive tree. in 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings. vol. 2015-December, 7351392, IEEE Computer Society, pp. 3190-3194, IEEE International Conference on Image Processing, ICIP 2015, Quebec City, Canada, 15/9/27. https://doi.org/10.1109/ICIP.2015.7351392

Fast affine-invariant image matching based on global Bhattacharyya measure with adaptive tree. / Son, Jongin; Kim, Seungryong; Sohn, Kwanghoon.

2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings. Vol. 2015-December IEEE Computer Society, 2015. p. 3190-3194 7351392.

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

TY - GEN

T1 - Fast affine-invariant image matching based on global Bhattacharyya measure with adaptive tree

AU - Son, Jongin

AU - Kim, Seungryong

AU - Sohn, Kwanghoon

PY - 2015/12/9

Y1 - 2015/12/9

N2 - Establishing visual correspondence is one of the most fundamental tasks in many applications of computer vision fields. In this paper we propose a robust image matching to address the affine variation problems between two images taken under different viewpoints. Unlike the conventional approach finding the correspondence with local feature matching on fully affine transformed-images, which provides many outliers with a time consuming scheme, our approach is to find only one global correspondence and then utilizes the local feature matching to estimate the most reliable inliers between two images. In order to estimate a global image correspondence very fast as varying affine transformation in affine space of reference and query images, we employ a Bhattacharyya similarity measure between two images. Furthermore, an adaptive tree with affine transformation model is employed to dramatically reduce the computational complexity. Our approach represents the satisfactory results for severe affine transformed-images while providing a very low computational time. Experimental results show that the proposed affine-invariant image matching is twice faster than the state-of-the-art methods at least, and provides better correspondence performance under viewpoint change conditions.

AB - Establishing visual correspondence is one of the most fundamental tasks in many applications of computer vision fields. In this paper we propose a robust image matching to address the affine variation problems between two images taken under different viewpoints. Unlike the conventional approach finding the correspondence with local feature matching on fully affine transformed-images, which provides many outliers with a time consuming scheme, our approach is to find only one global correspondence and then utilizes the local feature matching to estimate the most reliable inliers between two images. In order to estimate a global image correspondence very fast as varying affine transformation in affine space of reference and query images, we employ a Bhattacharyya similarity measure between two images. Furthermore, an adaptive tree with affine transformation model is employed to dramatically reduce the computational complexity. Our approach represents the satisfactory results for severe affine transformed-images while providing a very low computational time. Experimental results show that the proposed affine-invariant image matching is twice faster than the state-of-the-art methods at least, and provides better correspondence performance under viewpoint change conditions.

UR - http://www.scopus.com/inward/record.url?scp=84956660683&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84956660683&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2015.7351392

DO - 10.1109/ICIP.2015.7351392

M3 - Conference contribution

VL - 2015-December

SP - 3190

EP - 3194

BT - 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings

PB - IEEE Computer Society

ER -

Son J, Kim S, Sohn K. Fast affine-invariant image matching based on global Bhattacharyya measure with adaptive tree. In 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings. Vol. 2015-December. IEEE Computer Society. 2015. p. 3190-3194. 7351392 https://doi.org/10.1109/ICIP.2015.7351392