Performance Analysis of Different Restoration Techniques for Degraded 3d Cervical Spine Mri Image
Neelam Turk1*
, Sangeeta Kamboj2 , Sonam Khera1 and Neha Rajput11Electronics and Communication Engineering Department, J.C.Bose University of Science and Technology, YMCA ,Faridabad, Haryana, India. 121006.
2Electrical and Instrumentation Engineering Department, Thapar Institute of Engineering and Technology, Patiala, Punjab, India. 147001
Corresponding Author E-mail: engineersangeeta@gmail.com
Abstract: In the proposed work, noise models such as Salt & Pepper, Gaussian and Poisson are considered in order to corrupt the image.Image restoration is still challenging task to recover an original image using a degradation and restoration model. In the paper, Gaussian, Average and Wiener linear image restoration techniques are used to recover the original MRI image. Median filter, Min and Max non-linear filters are also used to obtain uncorrupt image in the paper.Mean square error (MSE), Peak Signal to Noise Ratio (PSNR) and Cross Correlation(CC) performance analysis criteria are used to compare different restoration technique so that better performance in a clinical diagnosis can be achieved. In the paper it can be found that wiener filter with 5 x 5 window for Gaussian, speckle and Poisson noise provides best performance in terms of MSE and PSNR. Also,median filter with 5 x 5 window gives better accuracy of results to restore 3D salt & pepper noised image in terms of MSE and CC.
Keywords: Image degradation; Image restoration; Linear and Nonlinear filter; MRI image; MSE; PSNR Back to TOC