Image denoising with multidirectional shrinkage in directionlet domain

The efficient representation of edges is key to improving the image denoising performance. This motivates us to capture the edges and represent them with a sparse description. A novel image denoising method is proposed by exploiting the sparse representation of the edges and the multidirectional shrinkage. The enhancement of the sparsity is achieved by applying directionlet transforms constructed with the directions of the edges. Because the constructed directionlet transforms are performed along different directions, for each pixel we obtain many different estimates, one of which is optimal. The final denoised output is obtained by a weighted averaging of all individual estimates. Experimental results show that our method, compared with other multidirectional wavelet-based denoising algorithms, can effectively remove noise and preserve detail information such as edges and textures while avoiding the border effect. We exploit the multidirectionality of the directionlet transform to reduce the noise.The constructed directionlet transforms with the local directions of the edges are separately applied the entire image.An efficient approach to calculating the slope value of the local direction is introduced.