Volume no :2, Issue no: 1, March (2015)

MEDICAL IMAGE FUSION BASED ON QUATERNION WAVELET TRANSFORM AND VISIBILITY FEATURE

Author's: Peng Geng, Xing Su and Tan Xu
Pages: [9] - [26]
Received Date: January 25, 2015; Revised March 11, 2015
Submitted by: Shuaiqi Liu.

Abstract

Medical image fusion is the process of registering and combining multiple images from single or multiple imaging modalities to improve the imaging quality and reduce redundant information. In this research, a fusion algorithm is proposed to combine one pairs of medical images, such as the CT-MRI images and CT-MRA images. The source medical images are firstly decomposed by the quaternion wavelet transform. In this method, the visibility feature conformed to human visual system is adopted to fused the quaternion wavelet coefficients. Owing to the shift-invariance of the quaternion wavelet coefficients, the proposed method is effective and can get satisfactory fusion results. This new method provides improved subjective and objectives results as compared to previous image fusion methods based on the redundant discrete wavelet transform, nonsubsampled contourlet transform, ripplet transform, and the NSDFB-DTCWT transform.

Keywords

QWT, image fusion, visibility feature.