Book contents
- Frontmatter
- Dedication
- Contents
- Preface
- Nomenclature
- 1 Overview of biomedical image analysis
- Part I Signals and systems, image formation, and image modality
- Part II Stochastic models
- Part III Computational geometry
- Part IV Variational approaches and level sets
- Part V Image analysis tools
- 11 Segmentation: statistical approach
- 12 Segmentation: variational approach
- 13 Basics of registration
- 14 Variational methods for shape registration
- 15 Statistical models of shape and appearance
- Index
- References
14 - Variational methods for shape registration
from Part V - Image analysis tools
Published online by Cambridge University Press: 05 November 2014
Book contents
- Frontmatter
- Dedication
- Contents
- Preface
- Nomenclature
- 1 Overview of biomedical image analysis
- Part I Signals and systems, image formation, and image modality
- Part II Stochastic models
- Part III Computational geometry
- Part IV Variational approaches and level sets
- Part V Image analysis tools
- 11 Segmentation: statistical approach
- 12 Segmentation: variational approach
- 13 Basics of registration
- 14 Variational methods for shape registration
- 15 Statistical models of shape and appearance
- Index
- References
Summary
Variational methods are based on continuous modelling of input data through the use of partial differential equations (PDE), which benefits from the well-developed theory and numerical methods on PDEs. A novel variational framework for global-to-local shape registration is presented. A new sum-of-squared-differences (SSD) criterion, which measures the disparity between the “implicit” representations of the input shapes, is introduced to recover the global alignment parameters. This new criterion has some advantages over existing ones in accurately handling scale variations. Complementary to the global registration field, the local deformation field is explicitly established between two globally aligned shapes, by minimizing an energy functional which incrementally updates the displacement field while keeping the corresponding implicit representation of the globally warped source shape as close as possible to a “signed distance” function. The optimization is performed under regularization constraints that enforce the smoothness of the recovered deformations. The overall process leads to a coupled set of equations that are simultaneously solved through a gradient descent scheme. The finite element (FE) approach for solving PDEs may be used to validate the performance of the shape registration technique. This chapter provides a holistic approach for shape registration.
Introduction
The process of registering shapes is based on three main components, namely (1) the way to represent the shapes, (2) the transformation model, and (3) the mathematical framework selected to recover the registration parameters. The following section briefly reviews each of these components.
- Type
- Chapter
- Information
- Biomedical Image AnalysisStatistical and Variational Methods, pp. 387 - 416Publisher: Cambridge University PressPrint publication year: 2014
References
, and , Non-rigid registration using distance functions, Comp. Vis. Image Understand. 89 (2003) 142–165.CrossRefGoogle Scholar
, and , Shape registration in implicit spaces using information theory and free form deformations. IEEE Trans. Pattern Anal. Mach. Intel. 28(8) (2006) 1303–1318.CrossRefGoogle ScholarPubMed
and , A variational approach for shapes registration using vector maps. Proc. IEEE Int. Conf. Image Processing (ICIP’06) April 12–16 (2006), Washington, DC, USA337–340.Google Scholar
, and , Shape representation and registration in vector implicit spaces: adopting a closed-form solution in the optimization process. IEEE Trans. Pattern Anal. Mach. Intel. 35 (2013) 763–768.CrossRefGoogle Scholar
, , and , Shape matching and object recognition using shape contexts. IEEE Trans. Pattern Anal. Mach. Intel. 24(24) (2002) 509–522.CrossRefGoogle Scholar
, and , Recognition of shapes by editing their shock graphs. IEEE Trans. Pattern Anal. Mach. Intel. 26(5) (2004) 550–571.CrossRefGoogle ScholarPubMed
and , Boundary finding with parametrically deformable models. IEEE Trans. Pattern Anal. Mach. Intel. 14(11) (1992) 1061–1075.CrossRefGoogle Scholar
, and , Approximately global optimization for robust alignment of generalized shapes. IEEE Trans. Pattern Anal. Mach. Intel. 33 (6) (2011) 1116–1131.Google ScholarPubMed
and , A new variational approach for 3D shape registration. Proc. Int. Symp. Biomedical Imaging (ISBI’07), April 12–15 (2007), Metro, Washington, DC, 1324–1327.Google Scholar
and , A global-to-local 2D shape registration in implicit spaces using level sets. Proc. IEEE Int. Conf. Image Processing (ICIP’07), September 16–19 (2007), St Antonio, Texas, VI-237–VI-240.Google Scholar
and , A novel shape registration framework and its application to 3D face recognition in the presence of expressions. 4th Int. Symp. Visual Computing (ISVC-08), December 1–3 (2008), Las Vegas, 287–296.Google Scholar
, Variational methods for multimodal image matching. Unpublished PhD thesis, Université de Nice – Sophia Antipolis (2002).
, Procrustes methods in the statistical analysis of shape. J. Roy. Stat. Soc. 53(2) (1991) 285–339.Google Scholar
, Visual pattern recognition by moment invariants. IRE Trans. Inform. Theory 49(8) (1962) 179–189.Google Scholar
, and , Affine-invariant geometric shape priors for region-based active contours. IEEE Trans. Pattern Anal. Mach. Intel., 28(8) (2006) 1352–1357.CrossRefGoogle ScholarPubMed
, and , Surface parametrization and shape description. Comp. Vis. Image Understand. 61(2) (1995) 154–170.CrossRefGoogle Scholar
, and , Rotation invariant spherical harmonic representation of 3D shape descriptors. In , (eds.) Eurographics Symposium on Geometry Processing’03 June 22–25 (2003) Aire-la-Ville, Switzerland.Google Scholar
, , , and , Weighted Fourier series representation and its application to quantifying the amount of gray matter. IEEE Trans. Med. Imag. (Special Issue on Computational Neuroanatomy) 26 (2007).Google ScholarPubMed
, and , Landmark-based registration using features identified through differential geometry. In , ed., Handbook of Medical Imaging, Waltham, MA: Academic Press (2000) ch. 31, 499–513.CrossRefGoogle Scholar
and , Curvature-based algorithms for nonrigid motion and correspondence estimation. IEEE Trans. Pattern Anal. Mach. Intel., 25(10) (2003) 1349–1354.CrossRefGoogle Scholar
, , et al., Shape modeling of the corpus callosum. Proc. 32nd IEEE Engineering in Medicine and Biology Society (EMBC) (2010) Buenos Aires, 4288–4291.Google Scholar
, A transformation for extracting new descriptors of shape. In (ed.), Models for the Perception of Speech and Visual Form. Cambridge: MIT Press (1967) 362–380.Google Scholar
and , 3D shape matching using skeleton graphs. In Simulation and Visualization, March 4–5 (2004) Magdeburg, 299–310.Google Scholar
, , and , Topology matching for fully automatic similarity estimation of 3D shapes. In SIGGRAPH’01: Proc. 28th Annual Conf. Computer Graphics and Interactive Techniques August 12–17 (2001), Los Angeles, CA, 203–212.Google Scholar
, , and , Robust segmentation of tubular structures in medical images. Proc. SPIE’08, San Diego, CA (2008).
and , PDE-based three dimensional path planning for virtual endoscopy. Proc. Information Processing in Medical Imaging 2005 (IPMI’05). Glenwood Springs, CO, July (2005) 529–540.Google Scholar
, , , and , The multiscale medial axis and its applications in image registration. Pattern Recogn. Lett. 15(5) (1994) 445–452.CrossRefGoogle Scholar
, , and , Segmentation, registration, and measurement of shape variation via image object shape. IEEE Trans. Med. Imaging, 18(10) (1999) 851–865.CrossRefGoogle ScholarPubMed
and , Variational curve skeletons using gradient vector flow. IEEE Trans. Pattern Anal. Mach. Intel. 31 (12), (2009) 2257–2274.CrossRefGoogle Scholar
and , Dynamic shapes of arbitrary dimension: The vector distance functions. Proc. 9th IMA Conf. Mathematics of Surfaces. London: Springer (2000). 227–262.Google Scholar
, , and , New deformable registration technique using scale space and curve evolution theory and a finite element based validation framework. 28th Annual Int. Conf. IEEE Engineering in Medicine and Biology Society, New York, August 31–Sept 3 (2006), 3041–3044.Google Scholar
, Variational methods for shape and image registrations. Unpublished PhD dissertation, Computer Vision and Image Processing Laboratory, University of Louisville (2008).
and , Rigid, affine and locally affine registration of free-form surfaces. Int. J. Comput. Vision 18(2) (1996) 99–119.CrossRefGoogle Scholar
, , and , Active shape models – their training and application. Comp. Vis. Image Understand. 61(1) (1995) 38–59.CrossRefGoogle Scholar
, , et al., A shape-based approach to the segmentation of medical imagery using level sets. IEEE Trans. Med. Imag., 22(2) (2003) 137–154.CrossRefGoogle ScholarPubMed
and , Reconciling distance functions and level sets. J. Vis. Commun. Image Repres. 11 (2000) 209–223.CrossRefGoogle Scholar
, , , and , A PDE-based fast local level set method. J. Comp. Phys., 155 (1999) 410–438.CrossRefGoogle Scholar
, , and , Level set evolution without re-initialization: A new variational formulation. Proc. IEEE Comp. Vis. Pattern Recog. (CVPR’2005), Vol. 1 (2005) 430–436.Google Scholar
, Mathematical Elasticity: Volume I: Three Dimensional Elasticity. North Holland: Elsevier (1988).Google Scholar