Image processing plays an important role in medical science for the analysis of heart attack and brain stroke. During the capturing of medical image some noise is induced and makes medical image blurred and unclear. So image de-nosing process is required to make the image noise free .In this paper we propose an image de-nosing method using subtraction transform and RBF neural network. The subtraction transform used basically in the field of voice noise reduction. the RBF neural network model is very efficient due to single layer network. The process of CT and MRI gets the high component value of noise in environment. For the reduction of these noise we have used spectral subtraction de-noising method. The spectral substation method is well recognized method for voice noise reduction. In spectral subtraction method the local noise component value are not considered. In this paper, we discuss image de-nosing methodology based on RBF neural network model comprised of radial biases neural network (RBF). The image features are extracted from the image using SSD function. RBF acts as a clustering mechanism that projects N-dimensional features from the SSD function into an M-dimensional feature space. The resulting vectors are fed into an RBF that categorizes them onto one of the relearned noise classes.

Medical Image, Noise, Subtraction Transform, RBF

[1]. M. Arcan, Paul A. Bottomley, Abdel-Monem and M. El-Sharkawy” de-noising mri using spectral subtraction” in ieee transactions on biomedical engineering, vol. 60, no. 6, june 2013.
[2]. Zhong, H., C. Yang and X. Zhang“A new weight for nonlocal means de-noising using method noise.” IEEE Signal Process. Lett, 2012.
[3]. M. A. Erturk, p. A. Bottomley, and a.-m. M. El-sharkawy, “spectral subtraction De-noising of mri,” in proc. 6th cairo int. Biomed. Eng. Conf., Cairo, egypt, 2012, Pp. 138–141.
[4]. Anupama, P., S.P. Kumar, B. Sudharshan and N. Pradhan” . A review of different image de-noising methods.” Int. J. Innov. Res. Dev, 2012. Pp 533-545.
[5]. Kadam, D.B., S.S. Gade, M.D. Uplane and R.K. Prasad” Neural network based brain tumor detection using MR images”. Int. J. Comp. Sci. Commun., 2011. Pp 325-231.
[6]. Cui, W., Y. Wang, Y. Fan, Y. Feng and T. Lei” Localized FCM clustering with spatial information for medical image segmentation and bias field estimation. “Int. J. Biomed. Imag. 2013.
[7]. Dahab, D.A., S.S.A. Ghoniemy and G.M. Selim” Automated brain tumor detection and identification using image processing and probabilistic neural network techniques.” Int. J. Comp. Image Process. Visual Commun., 1: 1-8,2013.
[8]. Kharat, K.D., P.P. Kulkarni and M.B. Nagori” Brain tumor classification using neural network based methods”in Int. J. Comput. Sci. Inform., 1: 85- 90.2012.
[9]. Xilin Liu, Zhengwei Ying, ShufangQiu “A Fourth-Order Partial Differential Equations Method Of Noise Removal” 4th International Congress on Image and Signal Processing, IEEE 2011.
[10]. JenyRajan, K. Kannan, M.R. Kaimal “An Improved Hybrid Model for Molecular Image De-noising” An Improved Hybrid Model for Molecular Image De-noising, Vol- 31, 2008. Pp 71-79.
[11]. M.J. FADILI, J.L. STARCK, F. MURTAGH “Inpainting and Zooming Using Sparse Representations” 2007. Pp 1-16.
[12]. Jian Bai ,Xiang-Chu Feng “Fractional-Order Anisotropic Diffusion for Image De-noising” TRANSACTIONS ON IMAGE PROCESSING, IEEE, VOL. 16, 2007. Pp 2492-2503.
[13]. Marius Lysaker, Xue-Cheng Tai, “Iterative Image Restoration Combining Total Variation Minimization and a Second-Order Functional” Springer: International Journal of Computer Vision, Volume 66, Issue 1, pp 5-18, January 2006, DOI:10.1007/s11263-005-3219-7, Print ISSN:0920-5691, Online ISSN:1573-1405.
[14]. Ben Arfia, F. “Choosing interpolation RBF function in image filtering with the Bidimentional Empirical Modal Decomposition ” in IEEE 2014