Optimal mass transport for deformable registration and warping of 2D images

Shamir, Reuben R1*
1.The Hebrew University of Jerusaelm
Abstract
Optimal mass transport for deformable registration and warping of 2D images

Abstract

We implement a warping method which is using the properties of elastic materials to compute the deformation between two images. The proposed elastic registration method incorporates the L2 Kantorovich-Wasserstein distance, also known as the Earth Mover’s Distance (EMD), as a similarity measure. The implemented paper presents an efficient partial differential equation approach for a first-order solution of this problem that is simpler than existing works suggested high-order solutions and is computationally simpler than existing works based on linear programming. Specifically, we implement the following paper Steven Haker, Lei Zhu, Allen Tannenbaum, and Sigurd Angenent, “Optimal mass transport for registration and warping”, International Journal of Computer Vision, 60(3), p. 225-240, 2004.

Keywords

Optimal mass transport warping deformable registration
Manuscript
Source Code and Data

Source Code and Data

code_optimal_mass_transportThumbs.db123 KBcloud_1.bmp155.5 KBcloud_2.bmp155.5 KBcomputeP.m1.3 KBcompute_density_map.m852 Bcompute_devergance.m564 Bcompute_gradient.m580 Bcompute_image_deformation_map.m3.2 KBcompute_initial_mapping.m3.6 KBcompute_jacobian.m615 Bcompute_mean_deformation_size.m422 Bcompute_optimal_mass_transport.m1.6 KBcompute_ut.m1.2 KBcompute_x_y_locations_image_0.m494 Bcreate_image_series.m1 KBcreate_test_images.m2.1 KBflame_1.bmp90.8 KBflame_2.bmp90.8 KBgradient_descent.m1.6 KBimread_to_gray.m797 Bmult_components.m677 Brotate_data.m434 Brun_tests.m9 KBsuperimpose.m633 Btest_u0_ax_1.bmp127.6 KBtest_u0_ax_2.bmp112.9 KBtest_u0_bxy_1.bmp127.6 KBtest_u0_bxy_2.bmp141 KBtransform.m963 Btransform_intensity.m1.1 KBu0_check.mat2.9 KBwater_1.jpg80 KBwater_2.jpg83.8 KB

Select a file to preview