Nonlinear Regression Color Correction Method for RGBN Cameras

Abstract

With the development of multi-spectral imaging techniques, many new multi-spectral imaging devices have been developed in recent years. Red-green-blue and near-infrared (RGBN) cameras are widely used because they capture visible light and near-infrared light simultaneously, but they inevitably introduce color desaturation. Because there is clear multicollinearity among the RGBN channels, the ordinary least squares regression (OLSR) color correction method performs poorly. To solve color bias and multicollinearity, an RGBN camera color correction pipeline is proposed. A large number of nonlinear regression color correction methods that consist of combinations of four regression methods and nine nonlinear transforms are evaluated in this study. The results show that the proposed OLSR-based compound transform color correction method and partial least-squares regression (PLSR) based Gaussian-core transform color correction method yield better color correction results and are more robust. These approaches reduce the multicollinearity of the RGBN camera channels and will be a valuable reference in the development of RGBN imaging applications. INDEX TERMS Color correction, multicollinearity near-infrared, nonlinear regression, RGBN camera.

A Modeling Approach on the Correction Model of the Chromatic Aberration of Scanned Wood Grain Images

“…However, color correction is mostly used in the distorted images caused by shooting environment [12,13] or in the chromatic aberration of optics themselves. Han et al [14] proposed an RGBN (Red-green-blue and Near-infrared) camera color correction pipeline to solve color bias and the multicollinearity of the imaging devices. Kozubek et al [15] invented a novel method of chromatic aberration measurement and software correction using sub-resolution bead imaging and computer image analysis.…”

Convolutional Neural Network Training for RGBN Camera Color Restoration Using Generated Image Pairs

“…RGBN cameras have wider spectral response than ordinary color visible cameras because of IRCF removal. They have a higher signal-to-noise ratio (SNR) but introduce extra color bias [2]. Hence, color restoration methods for RGBN cameras are necessary.…”

“…CCM methods that achieve satisfactory color correction results are widely used in Bayer CFA cameras, digital single lens reflex (DSLR) cameras, and mobile phone cameras. However, they do not work well on the RGBN camera color restoration task because of the more complicated color bias model and the arbitrary function form of reflection in scenes [2].The color bias is more severe for outdoor scenes with plants, as shown in Fig.2.…”

“…Monno et al [5] applied a quadratic polynomial CCM method proposed by Hong et al [6] and a root polynomial CCM method proposed by Finlayson et al [7] to the RGBN camera color restoration task and calibrated CCMs utilizing the chromatic values of color checker patches. Han et al [2] combined four kinds of regression methods and nine kinds of nonlinear methods and comprehensively studied CCM-based RGBN color restoration methods. Park et al [8][9][10] proposed spectral decomposition-based methods that decompose the NIR channel into a color-relevant band and a color-irrelevant band and optimized CCM with statistical properties of different channels.…”