A Global-to-Local Matching Strategy for Registering Retinal Fundus Images

Xinge You; Bin Fang; Zhenyu He; Yuan Yan Tang

doi:10.1007/11492429_32

A Global-to-Local Matching Strategy for Registering Retinal Fundus Images

Xinge You^*, Bin Fang, Zhenyu He, Yuan Yan Tang

^*Corresponding author for this work

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

7 Citations (Scopus)

Abstract

In this paper, a multi-resolution rigid-model-based global matching algorithm is employed to register tree structures of blood vessels extracted from retinal fundus images. To further improve alignment of the vessels, a local structure-deformed elastic matching algorithm is proposed to eliminate the existence of ‘ghost vessels’ for accurate registration. The matching methods are tested on 268 pairs of retinal fundus images. Experiment results show that our global-to-local registration strategy is able to achieve an average centreline mapping errors of 1.85 pixels with average execution time of 207 seconds. The registration results have also been visually validated by corresponding fusion maps.

Original language	English
Title of host publication	Pattern Recognition and Image Analysis
Subtitle of host publication	Second Iberian Conference, IbPRIA 2005, Estoril, Portugal, June 7-9, 2005, Proceedings, Part 1
Editors	Jorge S. Marques, Nicolás Pérez de la Blanca, Pedro Pina
Place of Publication	Berlin
Publisher	Springer
Pages	259-267
Number of pages	9
Edition	1st
ISBN (Electronic)	9783540322375
ISBN (Print)	9783540261537
DOIs	https://doi.org/10.1007/11492429_32
Publication status	Published - 13 May 2005
Event	2nd Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA 2005 - Estoril, Portugal Duration: 7 Jun 2005 → 9 Jun 2005 https://link.springer.com/book/10.1007/b136825 (Conference Proceedings)

Publication series

Name	Lecture Notes in Computer Science
Volume	3522
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Name	Image Processing, Computer Vision, Pattern Recognition, and Graphics

Name	IbPRIA: Iberian Conference on Pattern Recognition and Image Analysis

Conference

Conference	2nd Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA 2005
Country/Territory	Portugal
City	Estoril
Period	7/06/05 → 9/06/05
Internet address	https://link.springer.com/book/10.1007/b136825 (Conference Proceedings)

Access to Document

10.1007/11492429_32

Cite this

You, X., Fang, B., He, Z., & Tang, Y. Y. (2005). A Global-to-Local Matching Strategy for Registering Retinal Fundus Images. In J. S. Marques, N. P. D. L. Blanca, & P. Pina (Eds.), Pattern Recognition and Image Analysis: Second Iberian Conference, IbPRIA 2005, Estoril, Portugal, June 7-9, 2005, Proceedings, Part 1 (1st ed., pp. 259-267). (Lecture Notes in Computer Science; Vol. 3522), (Image Processing, Computer Vision, Pattern Recognition, and Graphics), (IbPRIA: Iberian Conference on Pattern Recognition and Image Analysis). Springer. https://doi.org/10.1007/11492429_32

You, Xinge ; Fang, Bin ; He, Zhenyu et al. / A Global-to-Local Matching Strategy for Registering Retinal Fundus Images. Pattern Recognition and Image Analysis: Second Iberian Conference, IbPRIA 2005, Estoril, Portugal, June 7-9, 2005, Proceedings, Part 1. editor / Jorge S. Marques ; Nicolás Pérez de la Blanca ; Pedro Pina. 1st. ed. Berlin : Springer, 2005. pp. 259-267 (Lecture Notes in Computer Science). (Image Processing, Computer Vision, Pattern Recognition, and Graphics). (IbPRIA: Iberian Conference on Pattern Recognition and Image Analysis).

@inproceedings{e1d81e546293462d855cc69061cef6fa,

title = "A Global-to-Local Matching Strategy for Registering Retinal Fundus Images",

abstract = "In this paper, a multi-resolution rigid-model-based global matching algorithm is employed to register tree structures of blood vessels extracted from retinal fundus images. To further improve alignment of the vessels, a local structure-deformed elastic matching algorithm is proposed to eliminate the existence of {\textquoteleft}ghost vessels{\textquoteright} for accurate registration. The matching methods are tested on 268 pairs of retinal fundus images. Experiment results show that our global-to-local registration strategy is able to achieve an average centreline mapping errors of 1.85 pixels with average execution time of 207 seconds. The registration results have also been visually validated by corresponding fusion maps.",

author = "Xinge You and Bin Fang and Zhenyu He and Tang, {Yuan Yan}",

note = "Publisher Copyright: {\textcopyright} Springer-Verlag Berlin Heidelberg 2005. Funding Information: This research was supported by a grant FRG/04-05/II-15 from Hong Kong Baptist University, a grant (60403011) from National Natural Science Foundation of China, a grant (2003ABA012) from Hubei Provincial Science and Technology Department, and a grant (20045006071-17) from Wuhan government, China.; 2nd Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA 2005 ; Conference date: 07-06-2005 Through 09-06-2005",

year = "2005",

month = may,

day = "13",

doi = "10.1007/11492429_32",

language = "English",

isbn = "9783540261537",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "259--267",

editor = "Marques, {Jorge S.} and Blanca, {Nicol{\'a}s P{\'e}rez de la } and Pedro Pina",

booktitle = "Pattern Recognition and Image Analysis",

address = "Germany",

edition = "1st",

url = "https://link.springer.com/book/10.1007/b136825",

}

You, X, Fang, B, He, Z & Tang, YY 2005, A Global-to-Local Matching Strategy for Registering Retinal Fundus Images. in JS Marques, NPDL Blanca & P Pina (eds), Pattern Recognition and Image Analysis: Second Iberian Conference, IbPRIA 2005, Estoril, Portugal, June 7-9, 2005, Proceedings, Part 1. 1st edn, Lecture Notes in Computer Science, vol. 3522, Image Processing, Computer Vision, Pattern Recognition, and Graphics, IbPRIA: Iberian Conference on Pattern Recognition and Image Analysis, Springer, Berlin, pp. 259-267, 2nd Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA 2005, Estoril, Portugal, 7/06/05. https://doi.org/10.1007/11492429_32

A Global-to-Local Matching Strategy for Registering Retinal Fundus Images. / You, Xinge; Fang, Bin; He, Zhenyu et al.
Pattern Recognition and Image Analysis: Second Iberian Conference, IbPRIA 2005, Estoril, Portugal, June 7-9, 2005, Proceedings, Part 1. ed. / Jorge S. Marques; Nicolás Pérez de la Blanca; Pedro Pina. 1st. ed. Berlin: Springer, 2005. p. 259-267 (Lecture Notes in Computer Science; Vol. 3522), (Image Processing, Computer Vision, Pattern Recognition, and Graphics), (IbPRIA: Iberian Conference on Pattern Recognition and Image Analysis).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - A Global-to-Local Matching Strategy for Registering Retinal Fundus Images

AU - You, Xinge

AU - Fang, Bin

AU - He, Zhenyu

AU - Tang, Yuan Yan

N1 - Publisher Copyright: © Springer-Verlag Berlin Heidelberg 2005. Funding Information: This research was supported by a grant FRG/04-05/II-15 from Hong Kong Baptist University, a grant (60403011) from National Natural Science Foundation of China, a grant (2003ABA012) from Hubei Provincial Science and Technology Department, and a grant (20045006071-17) from Wuhan government, China.

PY - 2005/5/13

Y1 - 2005/5/13

N2 - In this paper, a multi-resolution rigid-model-based global matching algorithm is employed to register tree structures of blood vessels extracted from retinal fundus images. To further improve alignment of the vessels, a local structure-deformed elastic matching algorithm is proposed to eliminate the existence of ‘ghost vessels’ for accurate registration. The matching methods are tested on 268 pairs of retinal fundus images. Experiment results show that our global-to-local registration strategy is able to achieve an average centreline mapping errors of 1.85 pixels with average execution time of 207 seconds. The registration results have also been visually validated by corresponding fusion maps.

AB - In this paper, a multi-resolution rigid-model-based global matching algorithm is employed to register tree structures of blood vessels extracted from retinal fundus images. To further improve alignment of the vessels, a local structure-deformed elastic matching algorithm is proposed to eliminate the existence of ‘ghost vessels’ for accurate registration. The matching methods are tested on 268 pairs of retinal fundus images. Experiment results show that our global-to-local registration strategy is able to achieve an average centreline mapping errors of 1.85 pixels with average execution time of 207 seconds. The registration results have also been visually validated by corresponding fusion maps.

UR - http://www.scopus.com/inward/record.url?scp=25144501976&partnerID=8YFLogxK

U2 - 10.1007/11492429_32

DO - 10.1007/11492429_32

M3 - Conference proceeding

AN - SCOPUS:25144501976

SN - 9783540261537

T3 - Lecture Notes in Computer Science

SP - 259

EP - 267

BT - Pattern Recognition and Image Analysis

A2 - Marques, Jorge S.

A2 - Blanca, Nicolás Pérez de la

A2 - Pina, Pedro

PB - Springer

CY - Berlin

T2 - 2nd Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA 2005

Y2 - 7 June 2005 through 9 June 2005

ER -

You X, Fang B, He Z, Tang YY. A Global-to-Local Matching Strategy for Registering Retinal Fundus Images. In Marques JS, Blanca NPDL, Pina P, editors, Pattern Recognition and Image Analysis: Second Iberian Conference, IbPRIA 2005, Estoril, Portugal, June 7-9, 2005, Proceedings, Part 1. 1st ed. Berlin: Springer. 2005. p. 259-267. (Lecture Notes in Computer Science). (Image Processing, Computer Vision, Pattern Recognition, and Graphics). (IbPRIA: Iberian Conference on Pattern Recognition and Image Analysis). doi: 10.1007/11492429_32

A Global-to-Local Matching Strategy for Registering Retinal Fundus Images

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this