Image fusion method based on adaptive pulse coupled neural network in the discrete fractional random transform domain

In this paper, we present a new approach for the remote sensing image fusion, which utilizes both adaptive pulse coupled neural network (PCNN) and the discrete fractional random transform in order to meet the requirements of both high spatial resolution and low spectral distortion. In the proposed scheme, the multi-spectral (MS) and panchromatic (Pan) images are converted to the discrete fractional random transform domains, respectively, which can make the spectrum distribute randomly and uniformly. In DFRNT spectrum domain, high amplitude spectrum (HAS) and low amplitude spectrum (LAS) components carry different information of original images. We take full advantage of pulse coupled neural network synchronization pulse issuance characteristics of PCNN to extract the HAS and LAS components properly, and give us the PCNN ignition mapping images which can be used to confirm the fusion parameters. In the fusion process, local standard deviation of amplitude spectrum is chosen as the link strength of pulse coupled neural network. Numerical simulations are performed to demonstrate that the proposed method is more reliable and superior than several existing methods based on Hue Saturation Intensity representation, Principal Component Analysis, the discrete fractional random transform, etc.