提出了一种基于邻域特征与脉冲发放皮层模型（Spiking Cortical Model，SCM）相结合的红外与可见光图像融合算法。首先，源图像经过非下采样剪切波变换（Non-subsampled Shearlet Transform， NSST）分解得到各自的低频子带图像和高频子带图像。然后，根据低频与高频子带的特点，选择适合的邻域特征作为 SCM的外部激励，通过比较 SCM的输出对低频与高频分量进行融合。最后将融合得到的低频与高频子带图像经逆变换重建得到最终的融合图像。通过实验仿真与其他几种方法进行比较，可以看出本文算法的融合图像红外目标突出，背景信息丰富，视觉效果良好，并且在标准差、信息熵，以及互信息等客观评价方面具有明显的提高。

A fusion algorithm of infrared and visible image is proposed based on neighborhood feature and the spiking cortical model(SCM). First, the source images are decomposed using the non-subsampled shearlet transform to get their own low-and high-frequency sub-band images. Then, according to the characteristics of the low-frequency and high-frequency sub-bands, suitable neighborhood features are chosen as the external excitation of SCM and both frequency components are fused by comparing the output of SCM. Finally, the low-frequency and high-frequency sub-band images are reconstructed by inverse transformation to obtain the final fusion image. A comparison with several other image fusion methods demonstrates that our proposed algorithm has an outstanding infrared target, rich background information, and good visual effect. Moreover, it is advantageous in objective evaluation parameters such as standard deviation, information entropy, and mutual information.