Abstract: In order to reduce the blocking artifacts resulted from Ttetrolet transform algorithm, Tetrolet transform was improved and Cycle Spinning was employed to avoid the blocking artifacts in this paper. And thus the improved Tetrolet transform was introduced and performed for image denoising. Some numerical experiments show the effectiveness and superiority of our technique. Compared with typical Tetrolet transform, the denoised images by our method are smoother, and the blocking artifacts is improved to some extent and inhibition. At the same time it can preserve more significant information of original images, such as local features, including image edges and image details. In addition, the proposed method gives better performance in Peak Signal to Noise Ratio (PSNR) and improves the quality of subjective and objective of image. Experimental results show that the proposed algorithm is effective and feasible, and can perform better on most data sets.