基于OMP算法的快速压缩感知图像重构

Fast compressed sensing image reconstruction based on OMP algorithm

针对正交匹配追踪(OMP)算法在压缩感知理论下的重构效果和所需时间相互矛盾的问题,基于子空间追踪(SP)算法的回溯思想,使用共轭梯度下降算法代替最小二乘法对正交匹配追踪(OMP)算法进行改进.并且对所改进算法的重构精度、重构稳定性进行了仿真实验,结果表明所提算法能保证重构质量良好并且有更好的重构速度和稳定性.

This paper proposed an improved OMP （Orthogonal Matching Pursuit）algorithm that replaced Ordinary Least Square algorithm with Conjugate Gradient Descent algorithm based on the backfitting idea of Subspace Pursuit algorithm, in order to solve the problem of contradiction between reconstruction effort and time required of OMP algorithm under compressive sensing theory.This paper also made simulation experiment on the accuracy and stability of reconstruction of the improved algorithm.The result showed that the improved algorithm made the quality of reconstruction satisfying with better speed and stability of reconstruction.