Infrared and visible image fusion method based on sparse features

Since the object information cannot be extracted efficiently by the traditional infrared and visible image fusion algorithms, an infrared and visible image fusion method based on the non-subsampled shearlet transform (NSST) and sparse structure features is proposed to retain the context information on visible image in this study. Firstly, we decompose the source images into low-frequency sub-band and high-frequency sub-band coefficients by the NSST. Then, benefit from the advantage of PCA on extracting principle information, the fusion rule in low-frequency sub-bands coefficients are merged by using the PCA-based approach. Afterwards, to retain the sparse structures from source images better, we propose a novel sparse feature extraction on high-frequency sub-band coefficients and fuse high-frequency components of source images. Finally, the inverse NSST is employed to obtain the fused image. The experimental results demonstrate that the proposed method preserves the background information on visible image and highlights the structural information on infrared image.