Abstract:

With regard to the fusion problem of grayscale visible light and infrared images, an adaptive fusion technique based on nonsubsampled contourlet transform (NSCT) and intensity hue saturation (IHS) transform is presented. With the help of the advantages of IHS transform, which can separate the intensity information from the spectrum information in the image, the color transfer approach is conducted to colorize the grayscale visible light image and the three component values of I, H and S can be gained. Multiscale and multidirection decomposition of the grayscale visible light image’s intensity component and infrared image are performed by NSCT. By adopting certain fusion rules, the lowfrequency and highfrequency components of the fusion image can be gained, besides, being the intensity component of the final fusion image, the grayscale fusion image can be also got by use of the inverse NSCT. Finally, the redgreenblue (RGB) colorized fusion image is reconstructed by the inverse IHS. The theory analysis and simulation examples show that the technique is effective.