基于模糊C-均值(FCM)聚类的模型具有在图像分割中可以保留原始图像中大部分信息的优点,自适应双通道脉冲发放皮层模型(ADSCM)具有全局耦合、脉冲同步、参数少、计算效率高以及可以很好地处理较暗区域信息等优点。提出了一种基于FCM与ADSCM的红外与可见光图像融合算法。源图像经过非下采样剪切波变换(NSST)分解后,通过将FCM与ADSCM相结合,对相应的子带图像进行融合,最终经过逆NSST得到重建的新图像。实验结果表明:该方法与其他传统方法相比,可以在保留可见光背景信息的同时有效地提取红外图像的目标信息;与其他几种方法相比,所提方法在平均梯度、互信息以及边缘保留因子等方面有明显的改进。

The model based on fuzzy C-mean (FCM) clustering has the advantage of retaining most of the information of the original image for image segmentation. The adaptive dual-channel spiking cortical model (ADSCM) has the advantages of global coupling, pulse synchronization, less parameters, and high computational efficiency, and can process the information of darker images well. An infrared and visible light image fusion algorithm based on FCM and ADSCM is proposed. After the source image is decomposed by non-subsampled shearlet transform (NSST), the corresponding sub-band images are fused by combining FCM and ADSCM, and finally the new image is reconstructed by inverse NSST. Experimental results show that compared with other traditional methods, the proposed method can effectively extract the target information of the infrared image while retaining the visible light background information, and has obvious improvement in average gradient, mutual information, and edge retention factor.