The objective of image processing is to denoise while keep the intrinsic imforrnation. A method is proposed for images denoising with double density dual-tree complex wavelet transform. It integrates the advantages of double density wavelet

dual tree wavelet and complex wavelet. It has improved directionality which increased the directions from 6 to 12. The adaptive soft threshold is applied to wavelet coefficients. It could ameliorate the ability of image denoising. The denoising and edge detection for a typical image is carried out. Simulated experiments demonstrate that the proposed approach is effective on image denoising and can keep the edge information at same time. Its mean square deviation is reduced 2.4% compared with the dual-tree complex wavelet.