WSEAS Transactions on Signal Processing
Print ISSN: 1790-5052, E-ISSN: 2224-3488
Volume 11, 2015
MRI Image Reconstruction Research Based on Discrete Shearlet Transform
Author:
Abstract: The two-dimensional wavelet transform for magnetic resonance imaging (MRI) does not represent sparsely curve singularity characteristics, it can only capture the limited direction information. In order to solve this problem, a new method for compressed sensing MRI (CS-MRI) is presented based on discrete shearlet transform in this paper. Frequency coefficients can be got at all scales and in all directions after discrete shearlet transform of MRI image. Then orthogonal matching pursuit algorithm is adopted to recover the sparsing coefficients. Finally, the reconstructed image is getten by inverse shearlet transform. Experimental results show that compared with wavelet transform, discrete shearlet transform for CS-MRI improves quality of reconstructed image and preserves more information about texture and edge.
Search Articles
Keywords: discrete shearlet transform, compressed sensing (CS), MRI image’s reconstruction, sparse expression, feature extraction
Pages: 157-163
WSEAS Transactions on Signal Processing, ISSN / E-ISSN: 1790-5052 / 2224-3488, Volume 11, 2015, Art. #19