论文部分内容阅读
该文提出一种采用HOPFIELE神经网络(HOPFIELD NEIRAL NETWORK简称HNN)优化的图象重建算法.将图象重建问题转化为HNN优化问题,取重建图象的峰值函数最小以及原始投影与再投影之间的误差平方和最小作为图象重建的优化目标,作为能量函数构造连续型HNN模型,由HNN能量函数极小化可得到重建问题的优化解.这种方法具有简单、计算量小、收敛快、便于并行计算等特点.对照ART算法,用计算机模拟产生的无噪声投影数据检验新算法,验证了新算法的优越性.“,”This paper preesents a solution algorithm for the image reconstruction problem based on the Hopfield neural network optimization. We viewed image reconstruction from projections as an HNN energyminimization problem by selecting two criteria as the optimization objection of reconstruction problem, which is simultaneous minimization of reconstructed image peakedness function and minimization of squared error between the original projection data and reprojection data doc to the reconstructed image. We designed a Hopfield neural network in continuous work--mode by mapping the objective function onto the energy funcation. We can find an optimal solution by minimizing the energy function. This offers the advantages: simplicity of the calculation, less computation, fast convergence and suit for parallel processing. Chmparisons of the re algorithm to ART algorithm are carried out using computer generated noised-free projections The results show that the proposed method is well.