DocumentCode :
2553392
Title :
Medical image fusion by combining SVD and shearlet transform
Author :
Biswas, Biswajit ; Ghoshal, Somoballi ; Chatterjee, Pubali ; Chakrabarti, Amlan ; Dey, Kashi Nath
Author_Institution :
Dept. of Comput. Sci. & Eng., Univ. of Calcutta, Kolkata, India
fYear :
2015
fDate :
19-20 Feb. 2015
Firstpage :
148
Lastpage :
153
Abstract :
The method of incorporating information from multiple images into a single image to get enhanced imaging quality and reduce randomness and redundancy in medical images for diagnosis and assessment of medical problems. In this paper, we present a new technique for medical image fusion using Singular Value Decomposition (SVD) method on Shearlet Transform (ST) domain to improve the information content of an image by fusing images like positron emission tomography (PET) and magnetic resonance imaging (MRI) images. The proposed method first transforms the source image into shearlet-image by using Shearlet Transform (ST). Then, we have used SVD model in low-pass sub-band and selected modified sub-bands according to their local characteristics. The composition of different high-pass subband coefficients are processed by ST decomposition. Then the high and the low sub-band are fused. Finally, the fused image is reconstructed by performing the inverse shearlet transform (IST). We have used three benchmark images to carry out our experiment and compare with many state-of-art techniques. Experimental results demonstrate that the proposed method outperforms many state-of-the-art techniques in both subjective and objective evaluation criteria.
Keywords :
image enhancement; image fusion; image reconstruction; inverse transforms; medical image processing; singular value decomposition; IST; MRI images; PET; ST decomposition; SVD method; enhanced imaging quality; high-pass subband coefficients; image reconstruction; inverse shearlet transform; low-pass sub-band; magnetic resonance imaging; medical image fusion; objective evaluation criteria; positron emission tomography; shearlet transform; singular value decomposition; subjective evaluation criteria; Biomedical imaging; Image fusion; Magnetic resonance imaging; Positron emission tomography; Principal component analysis; Signal processing algorithms; Transforms; Medical Image Fusion; Shearlet Transform; Singular Value Decomposition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing and Integrated Networks (SPIN), 2015 2nd International Conference on
Conference_Location :
Noida
Print_ISBN :
978-1-4799-5990-7
Type :
conf
DOI :
10.1109/SPIN.2015.7095385
Filename :
7095385
Link To Document :
بازگشت