Application of independent components analysis with the JADE algorithm and NIR hyperspectral imaging for revealing food adulteration

Abstract

a b s t r a c tIn recent years, Independent Components Analysis (ICA) has proven itself to be a powerful signal-processing technique for solving the Blind-Source Separation (BSS) problems in different scientific domains. In the present work, an application of ICA for processing NIR hyperspectral images to detect traces of peanut in wheat flour is presented. Processing was performed without a priori knowledge of the chemical composition of the two food materials. The aim was to extract the source signals of the different chemical components from the initial data set and to use them in order to determine the distribution of peanut traces in the hyperspectral images. To determine the optimal number of independent component to be extracted, the Random ICA by blocks method was used. This method is based on the repeated calculation of several models using an increasing number of independent components after randomly segmenting the matrix data into two blocks and then calculating the correlations between the signals extracted from the two blocks. The extracted ICA signals were interpreted and their ability to classify peanut and wheat flour was studied. Finally, all the extracted ICs were used to construct a single synthetic signal that could be used directly with the hyperspectral images to enhance the contrast between the peanut and the wheat flours in a real multi-use industrial environment. Furthermore, feature extraction methods (connected components labelling algorithm followed by flood fill method to extract object contours) were applied in order to target the spatial location of the presence of peanut traces. A good visualization of the distributions of peanut traces was thus obtained.

Independent components analysis (ICA) at the “cocktail-party” in analytical chemistry

“…The approach can contribute to the quality control of medicinal plants during and after cultivation. Another interesting application was to use ICA for processing NIR hyperspectral images to determine the spatial distribution of peanut traces as an allergenic food contaminant in wheat flour at different stages of food manufacturing [41].…”

Near-infrared hyperspectral imaging for non-destructive classification of commercial tea products

“…Often, the radiometric correction is sufficient to remove the effects of illumination inhomogeneity from the spectral data, however, when the sample surfaces are not uniform, as in the case of samples of loose tea leaves, the light scattering during diffuse reflection causes additive and multiplicative effects (Mishra et al, 2016). These scattering effects lead to baseline shifts in the spectrum and variation in the global intensity, which is again dependent on the wavelength.…”

“…Some applications of HSI of tea have been reported but these studies only considered a single variety of tea and measured the visible and very near infrared (VNIR) range (around 400-1000 nm), which is dominated by the pigments and physical characteristics of the samples (Zhao et al, 2009;Xie et al, 2015). In comparison to the VNIR region, the NIR region provides more detailed chemical information such as overtones resulting from the molecular vibration of O-H, C-H, N-H bonds and their combinations, which can support a better classification system based on the chemistry of the samples (Mishra et al, 2016).…”

Evaluation of Near-Infrared Hyperspectral Imaging for Detection of Peanut and Walnut Powders in Whole Wheat Flour

“…These indicated that for the two individual models, the limit of detection was 0.5%, while for the general model, the limit of detection was 1%. Mishra et al [3,32,33] studied the feasibility of the NIR HSI technique combined with principal component analysis (PCA), spectral band math, or independent component analysis (ICA) to detect peanut, hazelnut, and walnut particles (particle size of 1000-500 um) in wheat flour (particle size of 125-100 um and 212-160 um). The results of their Performance of the best PLSR models for (a) peanut-contaminated flour and (b) walnut-contaminated flour applied on prediction sets based on full spectra (an enlarged view of the green circle part was shown in the green pane).…”