The main aim of this paper is to reduce noise introduced by image enhancement methods based on the random spray sampling technique. Based on nature of sprays, output images of spray-based methods shows noise with unknown statistical distribution. The non-enhanced image is nothing but either free of noise or affected by noise of non-perceivable levels. The dual-tree complex wavelet transform (CWT) is a relatively recent enhancement to the discrete wavelet transform (DWT), with important additional properties: It is nearly shift invariant and directionally selective in two and higher dimensions. Across the six orientations of the DTWCT the standard deviation of non-enhanced image coefficients can be computed, and then it normalized for each level of the transform. The result is a map of the directional structures present in the non-enhanced image. Then Said map is used to shrink the coefficients of the enhanced image. According to data directionality the shrunk coefficients and the coefficients of the non-enhanced image are mixed. Finally, the enhanced image can be computed by doing the inverse transforms. The theoretical analyses of new algorithm are well verified via computer simulations.