PDF

Abstract:
We discuss a problem of comparison of two diffeomorphic images, namely, the source and target images of a diffeomorphism, which are given by two sets of points. The problem is solved on the basis of a method of constructing a minimized functional characterizing the evolution of the diffeomorphic source-to-target image transformation and a penalty for the image path deviation from the required trajectory. An algorithm for solving the diffeomorphic transformation equation is developed on the basis of the gradient descent method. The considered problem of comparison of two images can be used for constructing an optimal metamorphism of images, when there is no exact correspondence between the source and target images of the diffeomorphism.

Keywords:
pattern recognition, learning, Euler-Poincarè equation, diffeomorphic transformations, metamorphism.

Citation:
Lejhter SV, Chukanov SN. Matching of images based on their diffeomorphic mapping. Computer Optics 2018; 42(1): 96-104. DOI: 10.18287/2412-6179-2018-42-1-96-104.

References:

1. Beg M, Miller M, Trouvé A, Younes L. Computing large deformation metric mappings via geodesic flows of diffeomorphisms. International Journal of Computer Vision 2005; 61(2): 139-157. DOI: 10.1023/B:VISI.0000043755.93987.aa.
2. Miller M, Younes L. Group actions, homeomorphisms, and matching: a general framework. Int Journal of Computer Vision 2001; 41(1-2): 61-84. DOI: 10.1023/A:1011161132514.
3. Trouvé A, Younes L. Metamorphoses through lie group action. Foundations of Computational Mathematics 2005; 5(2): 173-198. DOI: 10.1007/s10208-004-0128-z.
4. Dolgovesov BS, Vyatkin SI. Perturbation functions in geometric modeling [In Russian]. Programmnye produkty i sistemy 2009; 4: 117-120.
5. Holm DD, Schmah T, Stoica C. Geometric mechanics and symmetry: from finite to infinite dimensions. Oxford: Oxford University Press; 2009. ISBN: 978-0-19-921290-3.
6. Chukanov SN. Definitions of invariants for n-dimensional traced vector fields of dynamic systems. Pattern Recognition and Image Analysis 2009; 19(2): 303-305. DOI: 10.1134/S105466180902014X.
7. Chukanov SN, Ulyanov DV. The formation of invariants for visualization of vector fields on the basis of constructing homotopy operator [In Russian]. Computer Optics 2012; 36(4): 622-626.
8. Holm DD, Trouvé A, Younes L. The Euler-Poincaré theory of metamorphosis. Quarterly of Applied Mathematics 2009; 67(4): 661-685. DOI: 10.1090/S0033-569X-09-01134-2.
9. Younes L, Arrate F, Miller MI. Evolutions equations in computational anatomy. NeuroImage 2009; 45(1): S40-S50. DOI: 10.1016/j.neuroimage.2008.10.050.
10. Arnold V. Sur la géométrie différentielle des groupes de Lie de dimension infinie et ses applications à l'hydrodynamique des fluides parfaits // Annales de l'institut Fourier 1966; 16(1): 319-361. DOI: 10.5802/aif.233.
11. Camassa R, Kuang D, Lee L. A geodesic landmark shooting algorithm for template matching and its applications. SIAM J Imaging Sci 2017; 10(1): 303-334. DOI: 10.1137/15M104373X.
12. Glaunès J, Qiu A, Miller M, Younes L. Large deformation diffeomorphic metric curve mapping. International Journal of Computer Vision 2008; 80(3): 317-336. DOI: 10.1007/s11263-008-0141-9.
13. Joshi S, Miller M. Landmark matching via large deformation diffeomorphisms. IEEE Transactions on Image Processing 2000; 9(8): 1357-1370. DOI: 10.1109/83.855431.
14. Grenander U, Miller M. Pattern theory: from representation to inference. Oxford: Oxford University Press; 2007. ISBN: 978-0-19-929706-1.
15. Younes L. Shapes and diffeomorphisms. Berlin, Heidelberg: Springer Science & Business Media; 2010.  ISBN: 978-3-642-12054-1.
16. Li SZ, Jain A, eds. Encyclopedia of biometrics. New York: Springer Publishing Company, Inc.; 2015.  ISBN: 978-1-4899-7487-7.

---

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20