Hyperspectral images of grapevine leaves including healthy leaves and leaves with biotic and abiotic symptoms.

A hyperspectral imaging database was collected on two hundred and five grape plant leaves. Leaves were measured with a hyperspectral camera in the visible/near infrared spectral range under controlled conditions. This dataset contains hyperspectral acquisition of grape leaves of seven different varieties. For each variety, acquisitions were performed on healthy leaves and leaves with foliar symptoms caused by different grapevine diseases showing clear symptoms of biotic or abiotic stress on other organs. For each leaf, chemical measurements such as chlorophyll and flavonol contents were also performed.

Visible - Near infrared hyperspectral dataset of healthy and infected apple tree leaves images for the monitoring of apple fire blight.

This dataset consists of three groups of hyperspectral images of apple tree plants. The first group of images consists of a temporal monitoring of seven apple tree plants, infected with fire blight (Erwinia amylovora), and six control plants over a period of 15 days. The second group of images includes a temporal monitoring of three infected plants, seven plants subjected to water stress, and seven control plants. The third group of images corresponds to acquisitions made in the orchard on nine trees showing symptoms of fire blight and six control trees. The pixel locations of infected areas have been provided for all images featuring symptomatic plants.

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).

Discriminating between Absorption and Scattering Effects in Complex Turbid Media by Coupling Polarized Light Spectroscopy with the Mueller Matrix Concept.

The separation of the combined effects of absorption and scattering in complex media is a major issue for better characterization and prediction of media properties. In this study, an approach coupling polarized light spectroscopy and the Mueller matrix concept were evaluated to address this issue. A set of 50 turbid liquid optical phantoms with different levels of scattering and absorption properties were made and measured at various orientations of polarizers and analyzers to obtain the 16 elements of the complete Mueller matrix in the VIS-NIR region. Partial least square (PLS) was performed to build calibration models from diffuse reflectance spectra in order to evaluate the potential of polarization spectroscopy through the elements of the Mueller matrix to predict physical and chemical parameters and hence, to discriminate scattering and absorption effects, respectively. In particular, it was demonstrated that absorption and scattering effects can be distinguished in the Rayleigh regime with linear and circular polarization from the M22 and M44 elements of the Mueller matrix, correspondingly.

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 New Optical Sensor Based on Laser Speckle and Chemometrics for Precision Agriculture: Application to Sunflower Plant-Breeding.

New instruments to characterize vegetation must meet cost constraints while providing accurate information. In this paper, we study the potential of a laser speckle system as a low-cost solution for non-destructive phenotyping. The objective is to assess an original approach combining laser speckle with chemometrics to describe scattering and absorption properties of sunflower leaves, related to their chemical composition or internal structure. A laser diode system at two wavelengths 660 nm and 785 nm combined with polarization has been set up to differentiate four sunflower genotypes. REP-ASCA was used as a method to analyze parameters extracted from speckle patterns by reducing sources of measurement error. First findings have shown that measurement errors are mostly due to unwilling residual specular reflections. Moreover, results outlined that the genotype significantly impacts measurements. The variables involved in genotype dissociation are mainly related to scattering properties within the leaf. Moreover, an example of genotype classification using REP-ASCA outcomes is given and classify genotypes with an average error of about 20%. These encouraging results indicate that a laser speckle system is a promising tool to compare sunflower genotypes. Furthermore, an autonomous low-cost sensor based on this approach could be used directly in the field.

Reduction of repeatability error for analysis of variance-Simultaneous Component Analysis (REP-ASCA): Application to NIR spectroscopy on coffee sample.

A method to reduce repeatability error in multivariate data for Analysis of variance-Simultaneous Component Analysis (REP-ASCA) has been developed. This method proposes to adapt the acquisition protocol by adding a set containing repeated measures for describing repeatability error. Then, an orthogonal projection is performed in the row-space to reduce the repeatability error of the original dataset. Finally, ASCA is performed on the orthogonalized dataset. This method was evaluated on NIR spectral data of coffee beans. This study shows that the repeatability error due to physical variations between measurements can alter results of the analysis of variance. These effects are predominant in factors analysis and can be seen on spectra as constant or non-constant baselines. By reducing repeatability error with REP-ASCA, baselines are removed and factor analysis provides more information about chemical content of the factors of interest.

Combining light polarization and speckle measurements with multivariate analysis to predict bulk optical properties of turbid media.

This study aims to investigate the combination of speckle pattern analysis, polarization parameters, and chemometric tools to predict the optical absorption and scattering properties of materials. For this purpose, an optical setup based on light polarization and speckle measurements was developed, and turbid samples were measured at 405 and 660 nm. First, a backscattered polarized speckle acquisition was performed on a set of 41 samples with various scattering (${\mu}_s$µs) and absorbing (${{\mu}_a}$µa) coefficients. Then, several parameters were computed from the polarized speckle images, and prediction models were built using stepwise multiple linear regression. For scattering media, ${{\mu}_s}$µs was predicted with ${R^{2} = 0.9}$R2=0.9 using two parameters. In the case of scattering and absorbing media, prediction results using two parameters were ${R^{2} = 0.62}$R2=0.62 for ${{\mu}_s}$µs and ${R^{2} = 0.8}$R2=0.8 for ${{\mu}_a}$µa. The overall results obtained in this research showed that the combination of speckle pattern analysis, polarization parameters, and chemometric tools to predict the optical bulk properties of materials show interesting promise.

Coupling Waveguide-Based Micro-Sensors and Spectral Multivariate Analysis to Improve Spray Deposit Characterization in Agriculture.

The leaf coverage surface is a key measurement of the spraying process to maximize spray efficiency. To determine leaf coverage surface, the development of optical micro-sensors that, coupled with a multivariate spectral analysis, will be able to measure the volume of the droplets deposited on their surface is proposed. Rib optical waveguides based on Ge-Se-Te chalcogenide films were manufactured and their light transmission was studied as a response to the deposition of demineralized water droplets on their surface. The measurements were performed using a dedicated spectrophotometric bench to record the transmission spectra at the output of the waveguides, before (reference) and after drop deposition, in the wavelength range between 1200 and 2000 nm. The presence of a hollow at 1450 nm in the relative transmission spectra has been recorded. This corresponds to the first overtone of the O-H stretching vibration in water. This result tends to show that the optical intensity decrease observed after droplet deposition is partly due to absorption by water of the light energy carried by the guided mode evanescent field. The probe based on Ge-Se-Te rib optical waveguides is thus sensitive throughout the whole range of volumes studied, i.e., from 0.1 to 2.5 µL. Principal Component Analysis and Partial Least Square as multivariate techniques then allowed the analysis of the statistics of the measurements and the predictive character of the transmission spectra. It confirmed the sensitivity of the measurement system to the water absorption, and the predictive model allowed the prediction of droplet volumes on an independent set of measurements, with a correlation of 66.5% and a precision of 0.39 µL.

PYM: a new, affordable, image-based method using a Raspberry Pi to phenotype plant leaf area in a wide diversity of environments.

BACKGROUND: Plant science uses increasing amounts of phenotypic data to unravel the complex interactions between biological systems and their variable environments. Originally, phenotyping approaches were limited by manual, often destructive operations, causing large errors. Plant imaging emerged as a viable alternative allowing non-invasive and automated data acquisition. Several procedures based on image analysis were developed to monitor leaf growth as a major phenotyping target. However, in most proposals, a time-consuming parameterization of the analysis pipeline is required to handle variable conditions between images, particularly in the field due to unstable light and interferences with soil surface or weeds. To cope with these difficulties, we developed a low-cost, 2D imaging method, hereafter called PYM. The method is based on plant leaf ability to absorb blue light while reflecting infrared wavelengths. PYM consists of a Raspberry Pi computer equipped with an infrared camera and a blue filter and is associated with scripts that compute projected leaf area. This new method was tested on diverse species placed in contrasting conditions. Application to field conditions was evaluated on lettuces grown under photovoltaic panels. The objective was to look for possible acclimation of leaf expansion under photovoltaic panels to optimise the use of solar radiation per unit soil area. RESULTS: The new PYM device proved to be efficient and accurate for screening leaf area of various species in wide ranges of environments. In the most challenging conditions that we tested, error on plant leaf area was reduced to 5% using PYM compared to 100% when using a recently published method. A high-throughput phenotyping cart, holding 6 chained PYM devices, was designed to capture up to 2000 pictures of field-grown lettuce plants in less than 2 h. Automated analysis of image stacks of individual plants over their growth cycles revealed unexpected differences in leaf expansion rate between lettuces rows depending on their position below or between the photovoltaic panels. CONCLUSIONS: The imaging device described here has several benefits, such as affordability, low cost, reliability and flexibility for online analysis and storage. It should be easily appropriated and customized to meet the needs of various users.