Two-Dimensional Object Localization by Coarse-to-Fine Correlation Matching

Part of Advances in Neural Information Processing Systems 6 (NIPS 1993)

Bibtex Metadata Paper


Chien-Ping Lu, Eric Mjolsness


We present a Mean Field Theory method for locating two(cid:173) dimensional objects that have undergone rigid transformations. The resulting algorithm is a form of coarse-to-fine correlation matching. We first consider problems of matching synthetic point data, and derive a point matching objective function. A tractable line segment matching objective function is derived by considering each line segment as a dense collection of points, and approximat(cid:173) ing it by a sum of Gaussians. The algorithm is tested on real images from which line segments are extracted and matched.