基于神经网络优化的少数投影最大熵层析图像重建算法

Maximum Entropy Image Reconstruction from Fewer Views Based on Neural Network

本文提出了一种基于连续型Hopfield神经网络(简称HNN)优化的少数投影最大熵层析图像重建算法。通过数值模拟,考察了该算法的可靠性和对场分布的重建效果以及抗噪声性能。结果表明,该算法具有较高的重建精度和良好的抗噪声性能。

Present a new algorithm for the reconstruction from fewer views by a maximum entropy approach based on the Hopfield neural network. The numerical simulation is used to study the effect of reconstruction and the stability against noise. The results show that this algorithm has fairly high accuracy and good stability against noise.