Abstract: A constrained conjugate gradient(CCG) restoration algorithm is proposed for badly blurred and noised high-energy radiography images. Constrained with prior knowledge, the algorithm converts the restoration problem to a constrained optimization one, which can be solved with the conjugate gradient algorithm. Since image restoration is an ill-posed problem, median filter and partial differential equation(PDE) are used to constrain the smoothness of deblurred image. Numerical experiment results show that the algorithm can properly retrieve edges and reduce noise simultaneously, and especially the signal to noise ratio(SNR) and subjective visual effect of the restored images are improved significantly.