Most existing compressed sensing reconstruction algorithms are based on single measurement vector.When processing image signal

the efficiency of these algorithms is low because the image is treated as one-dimension signal and the quality of the reconstructed image needs to be improved.A reconstruction algorithm based on multiple measurement vectors and sparse Bayesian learning is proposed in this paper.The image is reconstructed quickly because the weighting coefficient matrix can be got directly by processing each column of the measurement matrix simultaneously.The proposed algorithm has better reconstructed image and the efficiency has been improved significantly under the same sample rate.The validity of the proposed algorithm is proved by the experiments to the standard test images.