Wavelet based medical image fusion using filter masks

Abstract

This paper deals with convolution based image fusion using filter masks and reviews the performance of each with respect to qualitative and quantitative strategies. Fusion is performed using discrete wavelet transformation at two levels. The low and high frequency coefficients obtained are subjected to separate fusion rules. The low frequency approximation coefficients are selected based on a pixel selection rule while high frequency details are selected by convolution using averaging, gaussian, unsharp, prewitt and sobel filter masks of varying sizes. The performance evaluation in each case is conducted using objective strategies like RMSE and PSNR and results are graphically interpreted. Thus a comprehensive analysis is conducted to ensure the best fit mask for medical diagnosis and treatment applications. © 2010 Springer-Verlag.