Aristotle university of thessaloniki department of informatics l.jpg
Advertisement
This presentation is the property of its rightful owner.
1 / 26

ARISTOTLE UNIVERSITY OF THESSALONIKI. DEPARTMENT OF INFORMATICS PowerPoint PPT Presentation

ARISTOTLE UNIVERSITY OF THESSALONIKI. DEPARTMENT OF INFORMATICS 2D/3D Image Registration and Alignment: A Review Stelios Krinidis Presentation outline Definitions General aspects ICP algorithm Shape-based algorithm References Definitions Registration: a fundamental task in image

Related searches for ARISTOTLE UNIVERSITY OF THESSALONIKI. DEPARTMENT OF INFORMATICS

Download Presentation

ARISTOTLE UNIVERSITY OF THESSALONIKI. DEPARTMENT OF INFORMATICS

An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -

Presentation Transcript


Aristotle university of thessaloniki department of informatics l.jpg

ARISTOTLE UNIVERSITY OF THESSALONIKI.DEPARTMENT OF INFORMATICS

2D/3D Image Registration and Alignment:

A Review

Stelios Krinidis

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


Presentation outline l.jpg

Presentation outline

  • Definitions

  • General aspects

  • ICP algorithm

  • Shape-based algorithm

  • References

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


Definitions l.jpg

Definitions

  • Registration:a fundamental task in image

  • processing used to match two or more pictures taken,

  • for example, at different times, from different sensors,

  • or from different viewpoints.

  • Alignment:a fundamental task in image processing

  • used to match two or more pictures that are similar

  • but not alike, for example different sections from a 3D

  • object.

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


General aspects 1 l.jpg

General aspects (1)

  • Registration/Alignment can be used to:

  • 3D object reconstruction from its 2D sections.

  • 3D object visualization and morphological analysis.

  • Compare medical tissues (taken at different times)

  • showing tumor growth, internal abnormalities, etc.

  • Medical and surgical analysis, tests and simulations.

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


General aspects 2 l.jpg

General aspects (2)

  • Registration/Alignment (2D and 3D) compensation:

  • rotation and translation (MRI, CT, etc)

  • non-rigid transforms (physical sectioning of

  • biological tissues, anatomical atlases, etc)

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


General aspects 3 l.jpg

General aspects (3)

  • Proposed Registration/Alignment methods:

  • fiducial marker-based

  • feature-based using contours

  • crest lines or characteristics points

  • gray level-based

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


Iterative closest point icp l.jpg

Iterative Closest Point (ICP)

  • It can be used with the following representations of

  • geometrical data:

  • points sets

  • line segments (polylines)

  • implicit curves: g(x,y,z) = 0

  • parametric curves: (x(u),y(u),z(u))

  • triangle sets (faceted surfaces)

  • implicit surfaces: g(x,y,z) = 0

  • parametric surfaces: (x(u,υ),y(u,υ),z(u,υ))

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


Iterative closest point icp8 l.jpg

Iterative Closest Point (ICP)

  • Characteristics:

  • monotonic convergence to the nearest local minimum

  • rapid convergence during the first few iterations

  • global convergence depends on the initial parameters

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


Iterative closest point icp9 l.jpg

Iterative Closest Point (ICP)

Model point set:

Data point set:

Closest point set:

Distance metric:

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


Iterative closest point icp10 l.jpg

Iterative Closest Point (ICP)

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


Iterative closest point icp11 l.jpg

Iterative Closest Point (ICP)

Quaternion is the eigenvector related to the largest eigenvalue:

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


Iterative closest point icp12 l.jpg

Iterative Closest Point (ICP)

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


Iterative closest point icp13 l.jpg

Iterative Closest Point (ICP)

Point Set Matching

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


Iterative closest point icp14 l.jpg

Iterative Closest Point (ICP)

Curve Set Matching

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


Iterative closest point icp15 l.jpg

Iterative Closest Point (ICP)

Surface Set Matching

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


Shape based alignment l.jpg

Shape-Based Alignment

  • Alignment of 2D serially acquired sections forming a

  • 3D object

  • Characteristics:

  • shape-based algorithm (contours)

  • global energy function (expressing similarity between

  • neighboring slices).

  • no direction is privileged

  • no global offset

  • no error propagation

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


Shape based alignment17 l.jpg

Shape-Based Alignment

N :frame number

Nx:horizontal image dimension

Ny:vertical image dimension

R :neighborhood’s length

f :pixel similarity metric

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


Shape based alignment18 l.jpg

Shape-Based Alignment

Di :Distance Transform of image i

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


Shape based alignment19 l.jpg

Shape-Based Alignment

Distance Transform: each pixel has value equal to the pixel’s distance from the nearest non-zero pixel.

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


Shape based alignment20 l.jpg

Shape-Based Alignment

Alignment Errors Statistics

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


Shape based alignment21 l.jpg

Shape-Based Alignment

Alignment Errors Statistics

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


Shape based alignment22 l.jpg

Shape-Based Alignment

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


Shape based alignment23 l.jpg

Shape-Based Alignment

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


Shape based alignment24 l.jpg

Shape-Based Alignment

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


References l.jpg

References

  • P. Van den Elsen, E.J.D. Paul, and M.A.Viergever. Medical Image Matching – A review with classification. IEEE engineering in Medicine and Biology, 12(1):26-39, 1993.

  • M.J.Besl and N.McKay. A Method for the Registration of 3D Shapes. IEEE transactions of Pattern Analysis and Machine Intelligence(PAMI), 14(2):239-256, 1992

  • G.Borgefors. Hierarchical Chamfer Matching: A parametric edge matching algorithm. IEEE transactions of Pattern Analysis and Machine Intelligence(PAMI), 679-698, 1986.

  • W.Wells III, P.Viola, H.Atsumi, S.Nakajima, and R.Kikinis. Multimodal volume registration by maximization of mutual information. Medical Image Analysis, 1(1):33-51, 1996.

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


References26 l.jpg

References

  • C.Nikou, J.P.Armspach, F.Heitz, I.J.Namer, and D.Grucker. MR/MR and MR/SPECT registration of brain by fast stochastic optimization of robust voxel similarity measures NeuroImage, 8(1):30-43, 1998.

  • S.Krinidis, N.Nikolaidis, I.Pitas. Shape Based Alignment of 3-D Volume Slices. International Conference on Electronics, Circuits and Systems (ICECS'00) Kaslik, Lebanon, 17-20 September 2000.

Department of Informatics, Aristotle University of Thessaloniki, May 4, 2001


  • Login