关键词: 相位一致性, 空间频率, 脉冲耦合神经网络, 非下采样轮廓波变换, 多聚焦图像融合

Abstract: Since the traditional Pulse Coupled Neural Network-based (PCNN) image fusion methods cannot extract the focus region clearly, a multi-focus image fusion technique using Phase Congruency (PC) and Spatial Frequency (SF) combined with PCNN model in Non-Subsampled Contourlet Transform (NSCT) domain was proposed. Firstly, the source images were decomposed into high frequency subband and low frequency subband by NSCT. Secondly, the values of SF and PC were calculated to motivate PCNN neurons to fire to find the focus regions, and then the high and low frequency subbands were fused respectively. Lastly, the fused image was reconstructed through inverse NSCT. Multi-focus image datasets Clock, Pepsi and Lab were utilized as the experimental image sets. In comparison, four classical fusion methods and three newly put forward fusion algorithms were compared with the proposed algorithm. Objective indicators including mutual information, edge intensity, entropy, standard deviation and average gradient were calculated, and the values of the proposed method were greater than or very close to the maximum value of the comparison algorithms; meanwhile, it was clearly found from the difference maps between the experimental result image and the source image that the difference graph of the proposed method contained significantly fewer traces of the clear region of the source image. The experimental results indicate that the proposed method can better extract the clear region of the fused image, and it can better retain details such as edges and textures of the source images, thus, a superior fusion effect is acquired.

Key words: phase congruency, spatial frequency, Pulse Coupled Neural Network (PCNN), nonsubsampled contourlet transform, multi-focus image fusion