| 输入: 样本${\bf y}$, 采样矩阵$\Phi$, 稀疏度K | | 步骤1(识别): $\Lambda^{k} = \mathop{\arg\max}\limits _{\Upsilon\in\Gamma\setminus \Lambda_{k-1}}\mid \langle \Phi_{\Upsilon}, r^{k-1}\rangle\mid$ | | 步骤2(增加): $\Lambda_{k} = \Lambda_{k-1}\cup\Lambda^{k}$ | | 步骤3(估计): ${\bf x}^{(k)} = \mathop{\arg\min}\limits_{{\rm supp}({\bf u}) = \Lambda_{k}}\parallel {\bf y}-\Phi {\bf u}\parallel_{2}$ | | 步骤4(更新): ${\bf r}_{k} = {\bf y}-\Phi {\bf x}^{(k)}$ | | 输出: 重建信号${\bf x}^{(K)}$, 最优原子集$\Lambda_{K}$ |
|