Image Registration and Fusion using Moving Frame based Decomposition Framework Algorithm

Abstract

Image fusion is an important process in the medical image diagnostics methods. Fusing images by obtaining information from different source and different types of images(modals) called multi-modal image fusion. This paper implements an effective and fast spatial domain based multimodal image fusion using moving frame based decomposition (MFDF)method. Images from two different modalities are taken and decomposed to texture and approximation components. Weight mapping strategy is applied along with the guide filtering to fuse the approximation components using the final map. Weight mapping using the guide filtering is used for the fusing the images from different modalities. MATLAB is used for algorithm implementation. The results obtained are comparatively competitive with the recent publication[11]. Multi modal image fusion thus implemented gives promising results, when compared to moving frame decomposition framework method. The size and the blurring variable of the guiding filter is optimized to obtain a better Structural Similarity Index Measurement (SSIM).

A Review on the Rule-Based Filtering Structure with Applications on Computational Biomedical Images

“…To evaluate performance, 256 × 256 MRI, PET, and SPECT images are picked for the fused MRI/PET and MRI/SPECT images. The obtained results demonstrate that the proposed approach is not only better in terms of contour and edge detection, visual feature recognition, and computing performance, but also in terms of quantitative parameters when compared to other state-of-the-art offered systems, such as Fuzzy Transform with uniform sinusoidal membership fusion [ 84 ], PCNN model [ 85 , 86 ] for the fusion of LFS and HFS, local Laplacian filtering (LLF) [ 87 ] for image decomposition, contourlet transform (COT) [ 88 ], nonsubsampled contourlet transform (NSCT) [ 88 ], moving frame based decomposition framework (MFDF) [ 89 ], and sparse representation (SR) based approach [ 90 ].…”