A Transportation $L^p$ Distance for Signal Analysis

Abstract

Transport based distances, such as the Wasserstein distance and earth mover's distance, have been shown to be an effective tool in signal and image analysis. The success of transport based distances is in part due to their Lagrangian nature which allows it to capture the important variations in many signal classes. However these distances require the signal to be nonnegative and normalized. Furthermore, the signals are considered as measures and compared by redistributing (transporting) them, which does not directly take into account the signal intensity. Here we study a transport-based distance, called the $T{L}^p$ distance, that combines Lagrangian and intensity modelling and is directly applicable to general, non-positive and multi-channelled signals. The framework allows the application of existing numerical methods. We give an overview of the basic properties of this distance and applications to classification, with multi-channelled, non-positive one and two-dimensional signals, and color transfer.

References in corpus (11)

• Reconstruction of the early Universe as a convex optimization problem
• Imaging with Kantorovich-Rubinstein discrepancy
• The Radon cumulative distribution transform and its application to image classification
• Conformal Wasserstein distances: comparing surfaces in polynomial time
• A Sparse Multi-Scale Algorithm for Dense Optimal Transport
• Scaling Algorithms for Unbalanced Transport Problems
• Image Labeling by Assignment
• An efficient linear programming method for Optimal Transportation
• Transport-based analysis, modeling, and learning from signal and data distributions
• Wasserstein Training of Boltzmann Machines
• The Cumulative Distribution Transform and Linear Pattern Classification

Cited by in corpus (2)

• Joint Distribution Optimal Transportation for Domain Adaptation
• Large data limit for a phase transition model with the p-Laplacian on point clouds