Fusion of infrared and visible images based on fuzzy logic and guided filtering

摘要

Aiming at the problems of serious loss of detail and poor contrast in traditional infrared and visible fusion images, the thesis proposes an infrared and visible light image fusion method used fuzzy logic and guided filtering. First, the non-subsampled contourlet transform (NSCT) method is adopted to decompose the two original images in multi-scale and multi-direction, and the corresponding low-frequency(LFC) and high-frequency sub-generation coefficients(HFC) are obtained respectively. Then, adaptive fuzzy logic fusion rules are used for the low-frequency sub-band coefficients; for the high-frequency sub-band coefficients, the Laplacian energy sum function fusion rule based on guided filtering is used. Finally, the non-subsampled contourlet inverse transform is used to reconstruct the fusion image. The results find, compared with the existing methods, the image fused by this algorithm better retains the details of the source image's edge and texture, improves the clarity and contrast of the image, and can meet the visual needs of the human eye.