Nonlinear registration of binary shapes

Jozsef Nemeth, Csaba Domokos, Z. Kato

Research output: Conference contribution

4 Citations (Scopus)

Abstract

A novel approach is proposed to estimate the parameters of a diffeomorphism that aligns two binary images. Classical approaches usually define a cost function based on a similarity metric and then find the solution via optimization. Herein, we trace back the problem to the solution of a system of non-linear equations which directly provides the parameters of the aligning transformation. The proposed method works without any time consuming optimization step or established correspondences. The advantage of our algorithm is that it is easy to implement, less sensitive to the strength of the deformation, and robust against segmentation errors. The efficiency of the proposed approach has been demonstrated on a large synthetic dataset as well as in the context of an industrial application.

Original languageEnglish
Title of host publicationProceedings - International Conference on Image Processing, ICIP
PublisherIEEE Computer Society
Pages1101-1104
Number of pages4
ISBN (Print)9781424456543
DOIs
Publication statusPublished - 2009
Event2009 IEEE International Conference on Image Processing, ICIP 2009 - Cairo, Egypt
Duration: nov. 7 2009nov. 10 2009

Other

Other2009 IEEE International Conference on Image Processing, ICIP 2009
CountryEgypt
CityCairo
Period11/7/0911/10/09

Fingerprint

Binary images
Nonlinear equations
Cost functions
Industrial applications

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Nemeth, J., Domokos, C., & Kato, Z. (2009). Nonlinear registration of binary shapes. In Proceedings - International Conference on Image Processing, ICIP (pp. 1101-1104). [5413468] IEEE Computer Society. https://doi.org/10.1109/ICIP.2009.5413468

Nonlinear registration of binary shapes. / Nemeth, Jozsef; Domokos, Csaba; Kato, Z.

Proceedings - International Conference on Image Processing, ICIP. IEEE Computer Society, 2009. p. 1101-1104 5413468.

Research output: Conference contribution

Nemeth, J, Domokos, C & Kato, Z 2009, Nonlinear registration of binary shapes. in Proceedings - International Conference on Image Processing, ICIP., 5413468, IEEE Computer Society, pp. 1101-1104, 2009 IEEE International Conference on Image Processing, ICIP 2009, Cairo, Egypt, 11/7/09. https://doi.org/10.1109/ICIP.2009.5413468
Nemeth J, Domokos C, Kato Z. Nonlinear registration of binary shapes. In Proceedings - International Conference on Image Processing, ICIP. IEEE Computer Society. 2009. p. 1101-1104. 5413468 https://doi.org/10.1109/ICIP.2009.5413468
Nemeth, Jozsef ; Domokos, Csaba ; Kato, Z. / Nonlinear registration of binary shapes. Proceedings - International Conference on Image Processing, ICIP. IEEE Computer Society, 2009. pp. 1101-1104
@inproceedings{0c486da7ba18439186a3adde3d41d24b,
title = "Nonlinear registration of binary shapes",
abstract = "A novel approach is proposed to estimate the parameters of a diffeomorphism that aligns two binary images. Classical approaches usually define a cost function based on a similarity metric and then find the solution via optimization. Herein, we trace back the problem to the solution of a system of non-linear equations which directly provides the parameters of the aligning transformation. The proposed method works without any time consuming optimization step or established correspondences. The advantage of our algorithm is that it is easy to implement, less sensitive to the strength of the deformation, and robust against segmentation errors. The efficiency of the proposed approach has been demonstrated on a large synthetic dataset as well as in the context of an industrial application.",
keywords = "Binary image, Industrial inspection, Nonlinear deformation, Registration",
author = "Jozsef Nemeth and Csaba Domokos and Z. Kato",
year = "2009",
doi = "10.1109/ICIP.2009.5413468",
language = "English",
isbn = "9781424456543",
pages = "1101--1104",
booktitle = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Nonlinear registration of binary shapes

AU - Nemeth, Jozsef

AU - Domokos, Csaba

AU - Kato, Z.

PY - 2009

Y1 - 2009

N2 - A novel approach is proposed to estimate the parameters of a diffeomorphism that aligns two binary images. Classical approaches usually define a cost function based on a similarity metric and then find the solution via optimization. Herein, we trace back the problem to the solution of a system of non-linear equations which directly provides the parameters of the aligning transformation. The proposed method works without any time consuming optimization step or established correspondences. The advantage of our algorithm is that it is easy to implement, less sensitive to the strength of the deformation, and robust against segmentation errors. The efficiency of the proposed approach has been demonstrated on a large synthetic dataset as well as in the context of an industrial application.

AB - A novel approach is proposed to estimate the parameters of a diffeomorphism that aligns two binary images. Classical approaches usually define a cost function based on a similarity metric and then find the solution via optimization. Herein, we trace back the problem to the solution of a system of non-linear equations which directly provides the parameters of the aligning transformation. The proposed method works without any time consuming optimization step or established correspondences. The advantage of our algorithm is that it is easy to implement, less sensitive to the strength of the deformation, and robust against segmentation errors. The efficiency of the proposed approach has been demonstrated on a large synthetic dataset as well as in the context of an industrial application.

KW - Binary image

KW - Industrial inspection

KW - Nonlinear deformation

KW - Registration

UR - http://www.scopus.com/inward/record.url?scp=77951946286&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951946286&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2009.5413468

DO - 10.1109/ICIP.2009.5413468

M3 - Conference contribution

AN - SCOPUS:77951946286

SN - 9781424456543

SP - 1101

EP - 1104

BT - Proceedings - International Conference on Image Processing, ICIP

PB - IEEE Computer Society

ER -