自适应PCNN多聚焦图像融合

脉冲耦合神经网络（PNNN）型参数多,计算复杂,并且通常选取经验常数作为链接强度,这极大地限制了PCNN的普遍适用性.针对该问题,在分析PCNN模型基本特征的基础上,结合多聚焦图像的基本特点提出了一种基于PCNN的自适应多聚焦图像融合新方法.该方法在PCNN简化模型的基础上既将拉普拉斯能量作为PCNN对应神经元的链接强度β,又将其作为PCNN对应神经元的反馈输入经过PCNN点火从而获得每幅参与融合图像的点火映射图,最后通过选取适当的融合规则获得融合图像.实验结果表明了该方法的有效性,这种有效性不仅体现在视觉效果上,而且体现在客观评价标准上.

A Multi-focus Image Fusion Using Adaptive PCNN

Pulse coupled neural network （PCNN） model has many parameters,computational complexity, and select experience constant as linking strength,greatly limits the general applicability of PCNN.Aiming at the problem,this paper through the analysis of PCNN model and the basic characteristics of multi-focus image,multi-focus image fusion method is proposed for the adaptive PCNNIn this method,based on the PCNN simplified model,the Laplace energy is used as PCNN corresponding neurons＇ linking strength ,8 and as its feedback input,after the processing of PCNN,new fire mapping images are obtained for each image,and then the fused image is obtained by performing the appropriate algorithm.The experimental results show the effectiveness of the proposed method,the effectiveness is not only reflected in the visual effect,but also in the objective evaluation criteria.