A new image denoising algorithm based on the complex direction of filter bands and BlockShrink is proposed. The image is decomposed based on the complex direction of filter bands to obtain the coefficients. Then, according to the coefficient correlation, the block threshold method is used to select the best block size and the threshold. In this way, the unbiased risk estimation of each sub-band is minimized. The algorithm is entirely data-driven easy to implement and with good visual effects. Experiments show that the proposed algorithm increase the PSNR by 0.6 percent compared with the algorithm based on DWT-BlockShrink transform, and the edge and countour information are more clearly.