压缩感知中基于广义Jaccard系数的gOMP重构算法

g OMP reconstruction algorithm based on generalized Jaccard coefficient for compressed sensing

为了解决信号重构性能差的问题,提出了一种基于广义Jaccard系数的广义正交匹配追踪(generalized orthogonal matching pursuit,g OM P)重构算法。该算法利用广义Jaccard系数相似性匹配准则替换g OM P算法中的内积度量准则,优化了通过感知矩阵来选择与残差余量最匹配原子的匹配方式。实验结果表明,该算法的重构成功率不仅高于g OMP算法,同时也高于OMP、St OMP等算法。

In order to solve the problem such as lowreconstruction performance of the signal,we propose a generalized orthogonal matching pursuit（ g OM P） reconstruction algorithm based on generalized Jaccard coefficient. The improved g OM P algorithm replaces matching criterion of inner product by similarity matching criterion of generalized Jaccard coefficient,and selects the most matching atom from projection matrix and residual signal. Experimental results showthat the reconstruction success rate of proposed algorithm is much better than other algorithms,such as g OM P,OM P,St OM P and so on.