Comparison of different illumination systems for moisture prediction in cereal bars using hyperspectral imaging technology

Abstract

Moisture content and its distribution is a critical parameter in the production of cereal bars. Inappropriate control of this quality parameter can lead to non-conforming products and excess waste on production lines. In the field of hyperspectral imaging, the search for alternative light sources to stabilised-halogen (cheaper and emitting less heat) is a growing need for the application of this technology in industry. This study compares three different illumination systems for moisture prediction in the visible-near infrared (vis-NIR) range (from 400 nm to 1000 nm). The hyperspectral images were acquired using three illumination systems including two halogen-based systems (stabilised-halogen and conventional-halogen) and an LED-based illumination system. The results showed that halogen-based illumination systems combined with a partial least squares model better predicted moisture in bars. Lower accuracies were obtained when the experiment was performed with an LED-based illumination system, which showed double the error of the halogen-based systems. It was concluded that this is a consequence of the information lost in bands appearing above 850 nm that may be revealing information about the moisture in bars since the second overtone of the water O–H is found at 970 nm. The results demonstrate that conventional halogen-based light systems in the vis-NIR range are a promising method for moisture prediction in cereal bars.

Hyperspectral imaging as a non-destructive technique for estimating the nutritional value of food

“…SNV belongs to scatter-corrective methods that try to remove the scatter and optical path variations. This method eliminates the multiplicative interferences produced by the diffraction and difference in the particle size and its effect is independent of the original absorption values ( Barnes, R.J. et al, 1993 ; Echávarri-Dublán, J. et al, 2022 ). SNV centers and scales each spectra obtaining a mean value and variance equal to 0 and 1 respectively.…”

“…It is based on adjusting an appropriate polynomial degree for a small wavelength interval. This changes the original values but removes some of the noise that affects the spectra ( Todeschini, R. 1998 ; Echávarri-Dublán, J.et al, 2022 ). The second derivative removes linear and constant background noises.…”

“…The fundamental property of centered data is that the mean value of each of the variables is equal to zero. This pretreatment does not modify the variance of the data ( Todeschini, R. 1998 ; Echávarri-Dublán, J. et al, 2022 ). Finally, before modelling (except for PLS), a dimension reduction method was applied to the data, Principal Component Analysis (PCA).…”

Fraud detection in the fishing sector using hyperspectral imaging

“…Standard normal variate (SNV) scales and centers each spectrum obtaining a mean value and variance equal to 0 and 1 respectively. [20][21][22] In contrast, the most popular method based on a spectral derivate is the Savitzky-Golay method used to reduce the random noise appearing in the signal. Smoothing is based on adapting a polynomial of suitable degree for a short wavelength interval.…”