Computer Vision Studies Using Stochastic Resonance/Information-theoretic Methods

Abstract

An investigation into computer vision techniques is conducted using a procedure from nonlinear dynamics termed "stochastic resonance." This work involves concepts from detection theory, information theory and nonlinear dynamics. An information distance metric is synthesized which helps define the dependent measure to be used with the stochastic resonance optimization. Monte Carlo simulations show the efficacy of the proposed method. A class of test objects are presented to fairly evaluate the utility of the proposed methods introduced.