A novel infrared image fusion algorithm based on contourlet transform

Abstract

For processing multi-band infrared images detected by Multi-color IR Focal Plane Arrays (IRFPA), an image fusion algorithm is proposed based on contourlet transform (CT). Source images are firstly decomposed to the domain of the contourlet transform, the image fusion is then implemented in sub-bands with different scales and directions combining with special image fusion rules. By employing the parameters of Regional Energy (RE) and Local Relative Pixel Intensity (LRPI), which are calculated with the values of CT coefficients and the corresponding neighbor region, the algorithm integrates the approximation coefficients and the detail coefficients according to the parameters. Evaluations of the experiment results according to both the subjective and objective criteria, including average, mean square error, entropy and combined entropy, demonstrate that the algorithm based on CT with the proposed fusion rules is more effective than the ones based on CT with RE fusion rules and traditional method.