Welcome to Acta Armamentarii ! Today is

Acta Armamentarii ›› 2013, Vol. 34 ›› Issue (7): 815-820.doi: 10.3969/j.issn.1000-1093.2013.07.003

• Research Papers • Previous Articles     Next Articles

Fusion Method for Visible and Infrared Images Based on Non-subsampled Contourlet Transform and Sparse Representation

WANG Jun1, PENG Jin-ye1, HE Gui-qing1, FENG Xiao-yi1, YAN Kun2   

  1. 1. School of Electronics and Information, Northwestern Polytechnical University, Xi'an 710072, Shaanxi, China; 2. Academy of Space Electronic Information Technology, Xi'an 710000, Shaanxi, China
  • Received:2012-10-15 Revised:2012-10-15 Online:2014-08-19
  • Contact: WANG Jun E-mail:wangjun05062403@163. com

Abstract: An image fusion method based on NSCT and spare representation is presented for the lowersparseness of low-frequency sub-band coefficients unfavorable to fusion. Firstly, the infrared and visibleimages are transformed by NSCT, the common and innovation coefficients are extracted from the sparsecoefficients of low-frequency sub-band, and the sparse coefficients are adaptively weighted by the specificcoefficients. Secondly, the high-frequency sub-band coefficients with higher sparseness are fused by usinga method which takes the sum of absolute values of its coefficients be maximal at the same scale. Finally,the fusion image is reconstructed by the inverse NSCT. The method has better fusion performance than thetraditional fusion method based on DWT, NSCT, and the SOMP, JSR fusion method based on sparse representation.

Key words: information processing, image fusion, non-subsampled Contourlet transform, sparse representation, infrared image, visible image

CLC Number: