Multimodal Registration using the Discrete Wavelet Frame Transform

Abstract

Image registration is a critical step in medical image analysis. In this paper, a novel image registration method based on the discrete wavelet frame transform (DWFT) and the sum of absolute distance (SAD) method is proposed. First, the multimodal images are decomposed by DWFT, which is shift-invariant compared to traditional dyadic wavelet transforms. Then the energy maps are computed from the details sub-band images. Finally, genetic algorithm (GA) is adopted to obtain the minimum SAD between the two energy maps. The proposed method is tested on 50 pairs of two-dimensional T1-weighted and T2-weighted modal images. Experimental results demonstrated that the proposed method can achieve high accuracy in the rigid transformation case