Computation of discrete Fréchet distance using CNN

Abstract

The discrete Frechet distance basically measures the similarity of two curves considering their paths as well as distances of all discrete points on two curves. The present algorithms to compute the discrete Frechet distance between two curves have very high computational complexity. In order to reduce its computational burden, we propose a CNN architecture to compute the discrete Frechet Distance, employing the parallel processing capability of CNN consisting of an array of locally-coupled cells and each cell as a dynamical system. This paper presents the proposed CNN structure and its required cell coupling laws. The performance of the proposed system is verified through simulations.