Reconstruction of MR Images using Sparse Signal Sequences in Frequency Domain
Deepak M D1, Karthik P2, Sreedhar Kumar S3, Ravikumar H C4

1Deepak M D, Research scholar, Dept. of CSE, KSSEM, Bengaluru, India.
2Karthik P, Professor, Dept. Of ECE, KSSEM, Bengaluru, India.
3Sreedhar Kumar S, Professor, Dep of CSE, Dr. TTIT, KGF, Kolar, Karnataka, India.
4Ravikumar H C, Assistant Professor, Dept. of ECE, Gousia Engineering college, Ramanagaram, India.
Manuscript received on December 16, 2019. | Revised Manuscript received on December 22, 2019. | Manuscript published on January 10, 2020. | PP: 895-902 | Volume-9 Issue-3, January 2020. | Retrieval Number: B7885129219/2020©BEIESP | DOI: 10.35940/ijitee.B7885.019320
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: A new strategy for signal acquisition has emerged called Compressed Sensing (CS). The compressed sensing has gained attention in the filed of computer science, electrical engineering and mathematics. The Compressed Sensing is a mathematical approach of reconstructing a signal that is acquired from the dimensionally reduced data coefficients/less number of samples i.e. less than the Niquist rate. The data coefficients are high frequency component and low frequency component. The high frequency components are due to the rapid changes in the images (edges) and low frequency correspond provide the coarse scale approximation of the image, i.e. fine continuos surface. The idea is to retain only coarse scale approximation of the image i.e. the significant components that constitute the compressed signal. This compressed signal is the sparse signal which is so helpful during medical scenarios. During the Medical Resonance Imaging (MRI) scans, the patient undergoes many kinds difficulties like uncomfortness, patients are afraid of the scanning devices, h/she cannot be stable or changing his body positions slightly. Due to all these reasons, there can be a chance of acquiring only the less number of samples during the process of MRI scan. Even though the numbers of samples are less than the Nyquist rate, the reconstruction is possible by using the compressed sensing technique. The work has been carried out in the frequency domain to achieve the sparsity. The comparative study is done on percentage of different levels of sparsity of the signal. This can be verified by using Peak Signal Noise Ratio (PSNR), Mean Square Error (MSE) and Structural similarity (SSIM) methods which are calculated between the reference image and the reconstructed image. The finite dimensional signal has a sparsity and compressible representation. This sparsified data can be recovered from small set of linear, non-adaptive measurements. The implementation is done by using MATLAB. 
Keywords: Compressed Sensing, Magnetic Resonance Imaging (MRI), Niquist Rate, Sparsity.
Scope of the Article:  Signal and Image Processing