Open AccessMultimodal Medical Image Fusion using Guided Filter in NSCT Domain
Author(s) -
Nancy Mehta,
Sumit Budhiraja
Publication year - 2018
Publication title -
biomedical and pharmacology journal/biomedical and pharmacology journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.191
H-Index - 18
eISSN - 2456-2610
pISSN - 0974-6242
DOI - 10.13005/bpj/1566
Subject(s) - image fusion , fusion , contourlet , artificial intelligence , computer science , wavelet , filter (signal processing) , redundancy (engineering) , pattern recognition (psychology) , wavelet transform , computer vision , metric (unit) , image (mathematics) , engineering , operations management , operating system , philosophy , linguistics
Multimodal medical image fusion aims at minimizing the redundancy and collecting the relevant information using the input images acquired from different medical sensors. The main goal is to produce a single fused image having more information and has higher efficiency for medical applications. In this paper modified fusion method has been proposed in which NSCT decomposition is used to decompose the wavelet coefficients obtained after wavelet decomposition. NSCT being multidirectional,shift invariant transform provide better results.Guided filter has been used for the fusion of high frequency coefficients on account of its edge preserving property. Phase congruency is used for the fusion of low frequency coefficients due to its insensitivity to illumination contrast hence making it suitable for medical images. The simulated results show that the proposed technique shows better performance in terms of entropy, structural similarity index, Piella metric. The fusion response of the proposed technique is also compared with other fusion approaches; proving the effectiveness of the obtained fusion results.