Dual Tree Complex Wavelet Transform based Noise Reduction Technique

There has been a lot of research work concentrated towards noise reduction in image processing. However, with the wide spread of image usage, the development of new technique for noise reduction is become very important. This paper introduces the novel way to denoise the image, to reduce the noise which is introduced by a particular algorithm based on the random spray sampling technique used for image enhancement. Here a clearer version of an image is recovered from its noisy observation by use of Dual-tree complex wavelet transform (DTCWT). Unlike the discrete wavelet transform, DTCWT allows for distinction of data directionality in the transform space. In each level of the transform, the confirmed deviation of the non-enhanced image coefficient is computed across the DTCWT, then it is normalised which is used to shrink the coefficient of the enhanced image. The coefficients from the non-enhanced image and the shrunk coefficients are mixed and the enhanced image is computed via the inverse transform. An improvement in PSNR and SSIM are observed which clearly tells about the enhancement that can happen in the field of image processing by use of DTCWT.