Conjugate Variables as a Resource in Signal and Image Processing

Abstract

In this paper we develop a new technique to model joint distributions of signals. Our technique is based on quantum mechanical conjugate variables. We show that the transition probability of quantum states leads to a distance function on the signals. This distance function obeys the triangle inequality on all quantum states and becomes a metric on pure quantum states. Treating signals as conjugate variables allows us to create a new approach to segment them. Keywords: Quantum information, transition probability, Euclidean distance, Fubini-study metric, Bhattacharyya coefficients, conjugate variable, signal/sensor fusion, signal and image segmentation.