Training of templates for object recognition in invertible orientation scores : application to optic nerve head detection in retinal images

E.J. Bekkers; R. Duits; M. Loog

doi:10.1007/978-3-319-14612-6_34

Training of templates for object recognition in invertible orientation scores : application to optic nerve head detection in retinal images

E.J. Bekkers, R. Duits, M. Loog

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

6 Citations (Scopus)

Abstract

A new template matching scheme for the detection of objects on the basis of orientations is proposed. The matching scheme is based on correlations in the domain R2¿S1 of complex valued invertible orientation scores. In invertible orientation scores, a comprehensive overview of how an image is decomposed into local orientations is obtained. The presented approach allows for the efficient detection of orientation patterns in an intuitive and direct way. Furthermore, an energy minimization approach is proposed for the construction of suitable templates. The method is applied to optic nerve head detection in retinal images and extensive testing is done using images from both public and private databases. The method correctly identifies the optic nerve head in 99.7% of 1737 images.

Original language	English
Title of host publication	Energy Minimization Methods in Computer Vision and Pattern Recognition (10th International Conference, EMMCVPR 2015, Hong Kong, China, January 13-16, 2015. Proceedings)
Editors	X.C. Tai, E. Bae, T.F. Chan, M. Lysaker
Place of Publication	Berlin
Publisher	Springer
Pages	464-477
ISBN (Print)	978-3-319-14611-9
DOIs	https://doi.org/10.1007/978-3-319-14612-6_34
Publication status	Published - 2015
Event	10th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR 2015) - Hong Kong, China Duration: 13 Jan 2015 → 16 Jan 2015 Conference number: 10

Publication series

Name	Lecture Notes in Computer Science
Volume	8932
ISSN (Print)	0302-9743

Conference

Conference	10th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR 2015)
Abbreviated title	EMMCVPR 2015
Country/Territory	China
City	Hong Kong
Period	13/01/15 → 16/01/15

Access to Document

10.1007/978-3-319-14612-6_34

Cite this

Bekkers, E. J., Duits, R., & Loog, M. (2015). Training of templates for object recognition in invertible orientation scores : application to optic nerve head detection in retinal images. In X. C. Tai, E. Bae, T. F. Chan, & M. Lysaker (Eds.), Energy Minimization Methods in Computer Vision and Pattern Recognition (10th International Conference, EMMCVPR 2015, Hong Kong, China, January 13-16, 2015. Proceedings) (pp. 464-477). (Lecture Notes in Computer Science; Vol. 8932). Springer. https://doi.org/10.1007/978-3-319-14612-6_34

Bekkers, E.J. ; Duits, R. ; Loog, M. / Training of templates for object recognition in invertible orientation scores : application to optic nerve head detection in retinal images. Energy Minimization Methods in Computer Vision and Pattern Recognition (10th International Conference, EMMCVPR 2015, Hong Kong, China, January 13-16, 2015. Proceedings). editor / X.C. Tai ; E. Bae ; T.F. Chan ; M. Lysaker. Berlin : Springer, 2015. pp. 464-477 (Lecture Notes in Computer Science).

@inproceedings{3fb646f0c75c4487a8453f2a62ffc4d8,

title = "Training of templates for object recognition in invertible orientation scores : application to optic nerve head detection in retinal images",

abstract = "A new template matching scheme for the detection of objects on the basis of orientations is proposed. The matching scheme is based on correlations in the domain R2¿S1 of complex valued invertible orientation scores. In invertible orientation scores, a comprehensive overview of how an image is decomposed into local orientations is obtained. The presented approach allows for the efficient detection of orientation patterns in an intuitive and direct way. Furthermore, an energy minimization approach is proposed for the construction of suitable templates. The method is applied to optic nerve head detection in retinal images and extensive testing is done using images from both public and private databases. The method correctly identifies the optic nerve head in 99.7% of 1737 images.",

author = "E.J. Bekkers and R. Duits and M. Loog",

year = "2015",

doi = "10.1007/978-3-319-14612-6_34",

language = "English",

isbn = "978-3-319-14611-9",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "464--477",

editor = "X.C. Tai and E. Bae and T.F. Chan and M. Lysaker",

booktitle = "Energy Minimization Methods in Computer Vision and Pattern Recognition (10th International Conference, EMMCVPR 2015, Hong Kong, China, January 13-16, 2015. Proceedings)",

address = "Germany",

note = "10th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR 2015), EMMCVPR 2015 ; Conference date: 13-01-2015 Through 16-01-2015",

}

Bekkers, EJ, Duits, R & Loog, M 2015, Training of templates for object recognition in invertible orientation scores : application to optic nerve head detection in retinal images. in XC Tai, E Bae, TF Chan & M Lysaker (eds), Energy Minimization Methods in Computer Vision and Pattern Recognition (10th International Conference, EMMCVPR 2015, Hong Kong, China, January 13-16, 2015. Proceedings). Lecture Notes in Computer Science, vol. 8932, Springer, Berlin, pp. 464-477, 10th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR 2015), Hong Kong, China, 13/01/15. https://doi.org/10.1007/978-3-319-14612-6_34

Training of templates for object recognition in invertible orientation scores : application to optic nerve head detection in retinal images. / Bekkers, E.J.; Duits, R.; Loog, M.
Energy Minimization Methods in Computer Vision and Pattern Recognition (10th International Conference, EMMCVPR 2015, Hong Kong, China, January 13-16, 2015. Proceedings). ed. / X.C. Tai; E. Bae; T.F. Chan; M. Lysaker. Berlin: Springer, 2015. p. 464-477 (Lecture Notes in Computer Science; Vol. 8932).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Training of templates for object recognition in invertible orientation scores : application to optic nerve head detection in retinal images

AU - Bekkers, E.J.

AU - Duits, R.

AU - Loog, M.

N1 - Conference code: 10

PY - 2015

Y1 - 2015

N2 - A new template matching scheme for the detection of objects on the basis of orientations is proposed. The matching scheme is based on correlations in the domain R2¿S1 of complex valued invertible orientation scores. In invertible orientation scores, a comprehensive overview of how an image is decomposed into local orientations is obtained. The presented approach allows for the efficient detection of orientation patterns in an intuitive and direct way. Furthermore, an energy minimization approach is proposed for the construction of suitable templates. The method is applied to optic nerve head detection in retinal images and extensive testing is done using images from both public and private databases. The method correctly identifies the optic nerve head in 99.7% of 1737 images.

AB - A new template matching scheme for the detection of objects on the basis of orientations is proposed. The matching scheme is based on correlations in the domain R2¿S1 of complex valued invertible orientation scores. In invertible orientation scores, a comprehensive overview of how an image is decomposed into local orientations is obtained. The presented approach allows for the efficient detection of orientation patterns in an intuitive and direct way. Furthermore, an energy minimization approach is proposed for the construction of suitable templates. The method is applied to optic nerve head detection in retinal images and extensive testing is done using images from both public and private databases. The method correctly identifies the optic nerve head in 99.7% of 1737 images.

U2 - 10.1007/978-3-319-14612-6_34

DO - 10.1007/978-3-319-14612-6_34

M3 - Conference contribution

SN - 978-3-319-14611-9

T3 - Lecture Notes in Computer Science

SP - 464

EP - 477

BT - Energy Minimization Methods in Computer Vision and Pattern Recognition (10th International Conference, EMMCVPR 2015, Hong Kong, China, January 13-16, 2015. Proceedings)

A2 - Tai, X.C.

A2 - Bae, E.

A2 - Chan, T.F.

A2 - Lysaker, M.

PB - Springer

CY - Berlin

T2 - 10th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR 2015)

Y2 - 13 January 2015 through 16 January 2015

ER -

Bekkers EJ, Duits R, Loog M. Training of templates for object recognition in invertible orientation scores : application to optic nerve head detection in retinal images. In Tai XC, Bae E, Chan TF, Lysaker M, editors, Energy Minimization Methods in Computer Vision and Pattern Recognition (10th International Conference, EMMCVPR 2015, Hong Kong, China, January 13-16, 2015. Proceedings). Berlin: Springer. 2015. p. 464-477. (Lecture Notes in Computer Science). doi: 10.1007/978-3-319-14612-6_34

Training of templates for object recognition in invertible orientation scores : application to optic nerve head detection in retinal images

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this