Parameter adaptive unit-linking dual-channel PCNN based infrared and visible image fusion

Chinmaya Panigrahy, Ayan Seal, Nihar Kumar Mahato

Abstract: Highlights•A novel parameter adaptive unit-linking dual-channel pulse coupled neural network (PAUDPCNN) is proposed.•Fractal dimension (FD) is used to motivate the linking strengths of the proposed PADCPCNN model while fusing band-pass directional sub-bands whereas multiscale morphological gradients based linking strengths are used to fuse low-pass sub-bands.•A new infrared-visible image fusion method is proposed in nonsubsampled contourlet transform that uses the PAUDPCNN model to fuse the band-pass directional sub-bands and the low-pass sub-bands.•The performance of the proposed fusion framework is compared with eleven well known state-of-the-art methods using six fusion quality metrics.