为提高融合图像的细节表现力和信息冗余度, 针对红外与可见光图像, 提出一种基于有限离散剪切波变换(FDST)和双通道脉冲耦合神经网络(PCNN)的图像融合方法。首先, 利用FDST分解红外与可见光图像得到各自的高低频子带系数; 再对高低频子带系数分别采用不同链接强度的改进的空间频率激励的双通道PCNN进行融合; 最后, 通过FDST反变换得到融合图像。实验结果表明该算法能够有效增强图像清晰度和整体视觉效果, 融合效果跟其他融合方法相比, 在互信息、边缘信息传递量、标准差多个客观评价指标上具有明显提高。

To enhance fusion effects of infrared and visible images in detail preservation and information redundancy, a novel fusion method based on Finite Discrete Shearlet Transform (FDST) and dual-channel Pulse Coupled Neuron Network (PCNN) was proposed. Firstly, the original images were decomposed into low-frequency and high-frequency subband images by FDST; Secondly, low-frequency and high-frequency subband images were fused by modified-spatial-frequency motivated dual-channel PCNN with different linking strengths; Finally, the final fused image was reconstructed from fused subband images by inverse FDST. Experimental results indicate that the proposed fusion method can improve the overall visual performance and the image quality. Compared with other fusion methods, the proposed fusion method gets significant improvement in objective evaluation criteria of mutual information, edge information preservation and standard deviation.