Compressive sensing(CS) is an emerging research field that
has applications in signal processing, error correction, medical
imaging, seismology, and many more other areas. CS promises to
efficiently reconstruct a sparse signal vector via a much smaller
number of linear measurements than its dimension. In order
to improve CS reconstruction performance, this paper present
a novel reconstruction greedy algorithm called the Enhanced
Orthogonal Matching Pursuit (E-OMP). E-OMP falls into the
general category of Two Stage Thresholding(TST)-type algorithms
where it consists of consecutive forward and backward stages.
During the forward stage, E-OMP depends on solving the least
square problem to select columns from the measurement matrix.
Furthermore, E-OMP uses a simple backtracking step to detect
the previous chosen columns accuracy and then remove the false
columns at each time. From simulations it is observed that E-OMP
improve the reconstruction performance better than Orthogonal
Matching Pursuit (OMP) and Regularized OMP (ROMP).