Near-infrared fusion via a series of transfers for noise removal

Near-infrared imaging has been considered as a solution for providing high quality photographs in dim lighting conditions. This imaging system captures two types of multimodal images, namely, near-infrared gray image (NGI) and visible color image (VCI). NGI is noise free and grayscale, whereas the VCI has colors and contains noise. Moreover, there are significant edge and brightness discrepancies between NGI and VCI. In order to deal with this problem, a new transfer-based fusion method is proposed for noise removal. Different from conventional fusion approaches, the proposed method conducts a series of transfers, namely, contrast, detail, and color transfers. First, the proposed contrast and detail transfers aim at solving the serious discrepancy problem to create a new noise-free and detail-preserving NGI. Second, the proposed color transfer models the unknown colors from the denoised VCI through a linear transform, and then transfers the natural-looking colors into the newly generated NGI. The experimental results show that the proposed transfer-based fusion method is highly successful in solving the discrepancy problem. The edges and textures are clearly described and the noise is completely removed from the fused images. Most of all, the proposed method is superior to the conventional fusion methods, guided filtering, and state-of-the-art fusion methods based on scale map and layer decomposition.