NSCT域内基于改进PCNN和区域能量的多光谱和全色图像融合方法

针对多光谱和全色图像的融合，提出了一种NSCT域内基于改进脉冲耦合神经网络（PCNN）和区域能量的融合方法。首先，利用NSCT将图像分解为一个低频子带和多个不同方向的带通子带。然后，对分解后的低频子带采用基于区域能量的自适应加权算法进行融合；在带通方向子带，结合改进的脉冲耦合神经网络，使用带通方向子带系数作为PCNN的外部输入激励，经过PCNN点火获得待融合图像的点火映射图，根据点火时间计算点火映射图的区域能量，通过判决算子选择待融合图像的带通方向子带系数作为融合系数。最后，对融合处理后的NSCT变换系数进行重构生成融合图像。实验结果显示:在迭代次数为100次时，与改进小波算法相比，标准差提高了9.48%，熵提高了0.95%，相关系数提高了21.56%，偏差指数降低了29.66%；与Contourlet算法相比，标准差提高了9.73%，熵提高了0.94%，相关系数提高了11.27%，偏差指数降低了9.45%；与NSCT算法相比，标准差提高了3.84%，熵提高了3.34%，相关系数提高了7.89%，偏差指数降低了7.42%。

Fusion method of multispectral and panchromatic images based on improved PCNN and region energy in NSCT domain

A fusion method of multispectral(MS) and panchromatic(PAN) images based on improved Pulse-Coupled Neural Network(PCNN) and region energy in Nonsubsampled Contourlet Transform(NSCT) domain was proposed. Firstly, the two original images were decomposed into a low frequency subband and more bandpass directional subbands by NSCT. Then, for the low frequency subband coefficients, an adaptive regional energy weighting image fusion algorithm was presented; while for the bandpass directional subband coefficients, based on improved PCNN, the bandpass directional subband coefficients was used as the linking strength. After processing PCNN with the linking strength, new fire mapping images were obtained. The fire mapping image region energy was calculated, and the fusion coefficients were decided by the compare-selection operator with the fire mapping image region energy. Finally, the fusion images were reconstructed by NSCT inverse transform. The experimental results show that, when the numbers of iterations are 100 times, respectively as comparing with that of improved wavelet method, Contourlet method and NSCT method: the standard deviation increases by 9.48%, 9.73% and 3.84%; the entropy by 0.95%, 0.94% and 3.34%; the correlation coefficient by 21.56%, 11.27% and 7.89%, and the deviation index reduces by 29.66%, 9.45% and 7.42%.