Near-infrared coloring via a contrast-preserving mapping model

Abstract

Near-infrared gray images captured together with visible color images have recently proven useful for image enhancement and restoration. This paper introduces a new coloring method for adding colors to near-infrared gray images via a contrast-preserving mapping model. A naive coloring method directly adds the colors from the visible color image to the near-infrared gray image; however, this method results in an unrealistic image because of the discrepancies in brightness and image structure between the near-infrared gray image and the luminance plane of the visible color image. To solve this problem, a local linear mapping model with a local contrast constraint is proposed to find the relation between the near-infrared gray image and the luminance plane of the visible color image. This contrast-preserving linear mapping model enables the creation of a new near-infrared gray image that has a similar appearance to the luminance plane of the visible color image, but preserves local contrasts of the near-infrared gray image. In addition, the proposed mapping model can be utilized to transfer the colors from the visible color image to the newly created near-infrared gray image. The experimental results show that the proposed method not only preserves the local contrast and details of the near-infrared gray image, but also transfers the realistic colors from the visible color image to the near-infrared gray image.