Infrared Image And Visible Light Image Fusion Based On Nonsubsampled Contourlet Transform And The Gradient Of Uniformity

• DOI: 10.4156/ijact.vol4.issue5.14
• Publication Date: 2012-04-02T07:16:48Z
• Authors: JianHua Adu -; MingHui Wang -; ZhenYa Wu -; Jun Hu -
• Keywords: Contourlet; Image gradient

The nonsubsampled contourlet transform (NSCT) is a new multi-resolution transform, which can give an asymptotic representation of edges and contours in image by virtue its characteristics multi-direction, flexible multi-scale shift-invariant simultaneity. For fusion between visible light infrared image, this paper proposed method based on the visual region. Firstly, two original images were decomposed into different frequency sub-band coefficients using NSCT, then selection low subband coefficient bandpass direction was discussed respectively. choice coefficient, that chose region gradient characteristics. uses direct maximum regional uniformity obtained Finally, fused performing inverse NSCT combined coefficients. experimental results show algorithm achieved significant to extract target preserve edge target. At same time, it also good effectively details image.