In order to reduce the sampling rate of the traditional blind compressive sensing image recovery method,this paper proposes a novel blind compressive sensing image recovery approach.The method simultaneously exploits the local patch sparsity and nonlocal patch similarity.In addition,it employs an alternating direction method of multipliers to solve the resulting non-convex optimization problem.The method can accurately recover the original image.Experimental results have demonstrated that the proposed method can significantly reduce the sampling rate without sacrificing the quality of the reconstructed image.%为了降低传统的盲压缩感知图像重建方法所需求的采样率,提出了一种新的盲压缩感知图像重建方法,该方法同时考虑局部图像块的稀疏性和非局部图像块间的相似性,另外选择交替方向乘子算法求解产生的非凸优化问题,实现了图像的准确重建.实验结果表明,在不损失图像重构质量的情况下,该方法能够显著地降低采样率.
展开▼