摘要
基于图像最大熵分析,提出了一种基于Hopfield神经网络优化的图像恢复算法.将图像恢复问题转化为Hopfield神经网络优化问题,取恢复图像熵函数最大以及原始图像与恢复图像之间的误差平方和最小作为图像恢复的目标,构造能量函数连续型Hopfield神经网络模型,由Hopfield神经网络能量函数极小化可得到问题的优化解,其算法通过仿真实验,验证了算法的优越性.
Based on the analysis of maximum entropy for image,a solution algorithm for the image restoration problem is presented based on the Hopfield neural network optimization.We viewed image restoration from projections as Hopfield neural network energy minimization problem by selecting two criteria as the optimization objection of reconstruction problem,which is maximum of image entropy and minimization of squared error between the original image and restorative image due to the image restoration.And a Hopfield neural network in continuous work-mode is derived by mapping the objective function onto the energy function.We can find an optimal solution by minimizing the energy function.The results show that the proposed method is well.
出处
《湖南理工学院学报(自然科学版)》
CAS
2011年第1期34-37,共4页
Journal of Hunan Institute of Science and Technology(Natural Sciences)
基金
湖南省教育厅基金项目(10C0753)