Dataset containing spectral data from hyperspectral imaging and sugar content measurements of grapes berries in various maturity stage.

In the dataset presented in this article, two hundred and seventy four trays containing one hundred berries were measured by a hyperspectral camera in the visible/near-infrared spectral domain. This dataset was formed to study the use of hyperspectral imaging for maturity monitoring of grape berries [2]. This dataset contains reflectance spectra from hyperspectral camera of grape berries of three different varieties and chemical composition (sugar content).

Combination of multivariate curve resolution with factorial discriminant analysis for the detection of grapevine diseases using hyperspectral imaging. A case study: flavescence dorée.

Hyperspectral imaging is an emergent technique in viticulture that can potentially detect bacterial diseases in a non-destructive manner. However, the main problem is to handle the substantial amount of information obtained from this type of data, for which reliable data analysis tools are necessary. In this work, a combination of multivariate curve resolution-alternating least squares (MCR-ALS) and factorial discriminant analysis (FDA) is proposed to detect the flavescence dorée grapevine disease from hyperspectral imaging. The main purpose of MCR-ALS in this work was to provide chemically meaningful basic spectral signatures and distribution maps of the constituents needed to describe both healthy and infected leaf images by flavescence dorée. MCR scores (distribution maps) were used as the starting information for FDA to distinguish between healthy and infected pixels/images. Such an approach is presumably more powerful than the direct use of FDA on the raw imaging data, since MCR scores are compressed and noise-filtered information on pixel properties, which makes them more suitable for discrimination analysis. High levels of correct pixel discrimination rates (CR = 85.1%) for the MCR-ALS/FDA discrimination model were obtained. The model presents a lesser ability to determine infected leaves than healthy leaves. Nevertheless, only two images were misclassified. Therefore, the proposed strategy constitutes a good approach for the detection of flavescence dorée that could be potentially used to detect other phytopathologies.

A novel robust PLS regression method inspired from boosting principles: RoBoost-PLSR.

The calibration of Partial Least Square regression (PLSR) models can be disturbed by outlying samples in the data. In these cases the models can be unstable and their predictive potential can be depreciated. To address this problem, some robust versions of the PLSR Algorithm were proposed. These algorithms rely on the downweighting of these outliers during calibration. To this end, it is necessary to estimate an inconsistency measurement between the samples and the model. However, this estimation is not trivial in high dimensions. This paper proposes a novel robust PLSR algorithm inspired from the principles of boosting: RoBoost-PLSR. This method consists of realising a series of one latent variable weighted PLSR. RoBoost-PLSR is compared with the PLSR algorithm calibrated with and without outliers and also with Partial Robust M-regression (PRM), a reference robust method. This evaluation is conducted on the basis of three simulated datasets and a real dataset. Finally Roboost-PLSR proves to be resilient to the tested outliers, and can achieve the performances of the reference PLSR calibrated without any outlier.

Subpixel detection of peanut in wheat flour using a matched subspace detector algorithm and near-infrared hyperspectral imaging.

The detection of adulterations in food powder products represents a high interest especially when it concerns the health of the consumers. The food industry is concerned by peanut adulteration since it is a major food allergen often used in transformed food products. Near-infrared hyperspectral imaging is an emerging technology for food inspection. It was used in this work to detect peanut flour adulteration in wheat flour. The detection of peanut particles was challenging for two reasons: the particle size is smaller than the pixel size leading to impure spectral profiles; peanut and wheat flour exhibit similar spectral signatures and variability. A Matched Subspace Detector (MSD) algorithm was designed to take these difficulties into account and detect peanut adulteration at the pixel scale using the associated spectrum. A set of simulated data was generated to overcome the lack of reference values at the pixel scale and to design appropriate MSD algorithms. The best designs were compared by estimating the detection sensitivity. Defatted peanut flour and wheat flour were mixed in eight different proportions (from 0.02% to 20%) to test the detection performances of the algorithm on real hyperspectral measurements. The number and positions of the detected pixels were investigated to show the relevancy of the results and validate the design of the MSD algorithm. The presented work proved that the use of hyperspectral imaging and a fine-tuned MSD algorithm enables to detect a global adulteration of 0.2% of peanut in wheat flour.