Robust registration of serial cell microscopic images using 3D Hilbert scan search

Yongwen Lai, Seiichiro Kamata, Zhizhong Fu

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

Abstract

Microscopic images are quite helpful for us to observe the details of cells because of its high resolution. Furthermore it can benefit biologists and doctors to view the cell structure from any aspect by using a serial images to generate 3D cell structure. However each cell slice is placed at the microscopy respectively, which will bring in the arbitrary rotation and translation among the serial slices. What's more, the sectioning process will destroy the cell structure such as tearing or warping. Therefore we must register the serial slices before rendering the volume data in 3D. In this paper we propose a robust registration algorithm based on an improved 3D Hilbert scam search. Besides we put forward a simple but effective method to remove false matching in consecutive images. Finally we correct the local deformation based on optical-flow theory and adopt multi-resolution method. Our algorithm is tested, on a serial microscopy kidney cell images, and the experimental results show how accurate and robust of our method is.

Original languageEnglish
Title of host publicationProceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages530-533
Number of pages4
ISBN (Electronic)9784901122160
DOIs
Publication statusPublished - 2017 Jul 19
Event15th IAPR International Conference on Machine Vision Applications, MVA 2017 - Nagoya, Japan
Duration: 2017 May 82017 May 12

Other

Other15th IAPR International Conference on Machine Vision Applications, MVA 2017
CountryJapan
CityNagoya
Period17/5/817/5/12

Fingerprint

Microscopic examination
Optical flows

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Lai, Y., Kamata, S., & Fu, Z. (2017). Robust registration of serial cell microscopic images using 3D Hilbert scan search. In Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017 (pp. 530-533). [7986917] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/MVA.2017.7986917

Robust registration of serial cell microscopic images using 3D Hilbert scan search. / Lai, Yongwen; Kamata, Seiichiro; Fu, Zhizhong.

Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 530-533 7986917.

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

Lai, Y, Kamata, S & Fu, Z 2017, Robust registration of serial cell microscopic images using 3D Hilbert scan search. in Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017., 7986917, Institute of Electrical and Electronics Engineers Inc., pp. 530-533, 15th IAPR International Conference on Machine Vision Applications, MVA 2017, Nagoya, Japan, 17/5/8. https://doi.org/10.23919/MVA.2017.7986917
Lai Y, Kamata S, Fu Z. Robust registration of serial cell microscopic images using 3D Hilbert scan search. In Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 530-533. 7986917 https://doi.org/10.23919/MVA.2017.7986917
Lai, Yongwen ; Kamata, Seiichiro ; Fu, Zhizhong. / Robust registration of serial cell microscopic images using 3D Hilbert scan search. Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 530-533
@inproceedings{9a0a22f7307e4dc29206d2eadbd197e8,
title = "Robust registration of serial cell microscopic images using 3D Hilbert scan search",
abstract = "Microscopic images are quite helpful for us to observe the details of cells because of its high resolution. Furthermore it can benefit biologists and doctors to view the cell structure from any aspect by using a serial images to generate 3D cell structure. However each cell slice is placed at the microscopy respectively, which will bring in the arbitrary rotation and translation among the serial slices. What's more, the sectioning process will destroy the cell structure such as tearing or warping. Therefore we must register the serial slices before rendering the volume data in 3D. In this paper we propose a robust registration algorithm based on an improved 3D Hilbert scam search. Besides we put forward a simple but effective method to remove false matching in consecutive images. Finally we correct the local deformation based on optical-flow theory and adopt multi-resolution method. Our algorithm is tested, on a serial microscopy kidney cell images, and the experimental results show how accurate and robust of our method is.",
author = "Yongwen Lai and Seiichiro Kamata and Zhizhong Fu",
year = "2017",
month = "7",
day = "19",
doi = "10.23919/MVA.2017.7986917",
language = "English",
pages = "530--533",
booktitle = "Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Robust registration of serial cell microscopic images using 3D Hilbert scan search

AU - Lai, Yongwen

AU - Kamata, Seiichiro

AU - Fu, Zhizhong

PY - 2017/7/19

Y1 - 2017/7/19

N2 - Microscopic images are quite helpful for us to observe the details of cells because of its high resolution. Furthermore it can benefit biologists and doctors to view the cell structure from any aspect by using a serial images to generate 3D cell structure. However each cell slice is placed at the microscopy respectively, which will bring in the arbitrary rotation and translation among the serial slices. What's more, the sectioning process will destroy the cell structure such as tearing or warping. Therefore we must register the serial slices before rendering the volume data in 3D. In this paper we propose a robust registration algorithm based on an improved 3D Hilbert scam search. Besides we put forward a simple but effective method to remove false matching in consecutive images. Finally we correct the local deformation based on optical-flow theory and adopt multi-resolution method. Our algorithm is tested, on a serial microscopy kidney cell images, and the experimental results show how accurate and robust of our method is.

AB - Microscopic images are quite helpful for us to observe the details of cells because of its high resolution. Furthermore it can benefit biologists and doctors to view the cell structure from any aspect by using a serial images to generate 3D cell structure. However each cell slice is placed at the microscopy respectively, which will bring in the arbitrary rotation and translation among the serial slices. What's more, the sectioning process will destroy the cell structure such as tearing or warping. Therefore we must register the serial slices before rendering the volume data in 3D. In this paper we propose a robust registration algorithm based on an improved 3D Hilbert scam search. Besides we put forward a simple but effective method to remove false matching in consecutive images. Finally we correct the local deformation based on optical-flow theory and adopt multi-resolution method. Our algorithm is tested, on a serial microscopy kidney cell images, and the experimental results show how accurate and robust of our method is.

UR - http://www.scopus.com/inward/record.url?scp=85027860522&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027860522&partnerID=8YFLogxK

U2 - 10.23919/MVA.2017.7986917

DO - 10.23919/MVA.2017.7986917

M3 - Conference contribution

SP - 530

EP - 533

BT - Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -