Title: Monomodal registration with adaptive parameter computing

Authors: Murong Jiang, Yongyan Lin, Xiaojie Guo, Junfang Kang

Addresses: School of Information, Yunnan University, Kunming, 650091, China. ' School of Information, Yunnan University, Kunming, 650091, China. ' School of Information, Yunnan University, Kunming, 650091, China. ' School of Information, Yunnan University, Kunming, 650091, China

Abstract: Most implementations for image registration are produced by defining a similarity measure between two given images, then minimising an energy functional that combines both similarity and regularity measures. The registration result greatly relies on the weight parameter, which usually is given in advance, big or small parameter may produce the discontinuous deformation field or bad registration. In this paper, we discuss an adaptive parameter computing method for monomodal image registration, employ the energy functional with probability density function searching the weight parameter corresponding to the local degrees of variability in matching. Some experiments show that this method can be less sensitive to the choice of the parameter, drop the iteration step and save computation time.

Keywords: image registration; weight parameter; adaptive computing; probability density function; PDF; monomodal images; mathematical modelling.

DOI: 10.1504/IJCAT.2011.042243

International Journal of Computer Applications in Technology, 2011 Vol.41 No.1/2, pp.132 - 136

Published online: 01 Sep 2011 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article