Hyperspectral near infrared image calibration and regression

Mikko Mäkelä; Paul Geladi; Marja Rissanen; Lauri Rautkari; Olli Dahl

doi:10.1016/j.aca.2020.01.019

Hyperspectral near infrared image calibration and regression

Anal Chim Acta. 2020 Apr 8:1105:56-63. doi: 10.1016/j.aca.2020.01.019. Epub 2020 Jan 10.

Authors

Mikko Mäkelä¹, Paul Geladi², Marja Rissanen³, Lauri Rautkari³, Olli Dahl³

Affiliations

¹ Aalto University, School of Chemical Engineering, Department of Bioproducts and Biosystems, PO Box 16300, 00076, Aalto, Finland; Swedish University of Agricultural Sciences, Department of Forest Biomaterials and Technology, Skogsmarksgränd, 90183, Umeå, Sweden. Electronic address: mikko.makela@aalto.fi.
² Swedish University of Agricultural Sciences, Department of Forest Biomaterials and Technology, Skogsmarksgränd, 90183, Umeå, Sweden.
³ Aalto University, School of Chemical Engineering, Department of Bioproducts and Biosystems, PO Box 16300, 00076, Aalto, Finland.

PMID: 32138926
DOI: 10.1016/j.aca.2020.01.019

Abstract

Reference materials are used in diffuse reflectance imaging for transforming the digitized camera signal into reflectance and absorbance units for subsequent interpretation. Traditional white and dark reference signals are generally used for calculating reflectance or absorbance, but these can be supplemented with additional reflectance targets to improve the accuracy of reflectance transformations. In this work we provide an overview of hyperspectral image regression and assess the effects of reflectance calibration on image interpretation using partial least squares regression. Linear and quadratic reflectance transformations based on additional reflectance targets decrease average measurement errors and make it easier to estimate model pseudorank during image regression. The lowest measurement and prediction errors were obtained with the column and wavelength specific quadratic transformations which retained the spatial information provided by the line-scanning instrument and reduced errors in the predicted concentration maps.

Keywords: Hyperspectral imaging; Partial least squares; Prediction; Pseudorank; Reflectance calibration; Textile analysis.