Visualization of Hyperspectral Images Using Moving Least Squares

TL;DR

This paper introduces a nonlinear visualization method for hyperspectral images using Moving Least Squares to produce natural color images that preserve spectral information and are more interpretable for humans.

Contribution

It presents a novel MLS-based approach for hyperspectral image visualization that maintains natural colors and can be reused across images from the same sensor.

Findings

Produces natural color hyperspectral images

Preserves important visual information for analysis

Reuses matching pixel information across images

Abstract

Displaying the large number of bands in a hyper spectral image on a trichromatic monitor has been an active research topic. The visualized image shall convey as much information as possible form the original data and facilitate image interpretation. Most existing methods display HSIs in false colors which contradict with human's experience and expectation. In this paper, we propose a nonlinear approach to visualize an input HSI with natural colors by taking advantage of a corresponding RGB image. Our approach is based on Moving Least Squares, an interpolation scheme for reconstructing a surface from a set of control points, which in our case is a set of matching pixels between the HSI and the corresponding RGB image. Based on MLS, the proposed method solves for each spectral signature a unique transformation so that the non linear structure of the HSI can be preserved. The matching pixels between a pair of HSI and RGB image can be reused to display other HSIs captured b the same imaging sensor with natural colors. Experiments show that the output image of the proposed method no only have natural colors but also maintain the visual information necessary for human analysis.