No abstract

In this method, a numerical matrix comprised of ten color scales (RGB, HSV, L, and rgb) as independent variables from digitalized images was used as a proof of concept for the prediction of the mass, apparent volume, and bulk density parameters of grains for quality control considering postharvest purposes. The goal was to develop a high throughput multivariate regression model using partial least squares (PLS) combined with the information from color images to assess the raw product. The data set of external samples was successfully evaluated with standard error of cross-validation (SECV) values of 1.23 g (16.4-28.9), 2.03 cm 3 (20.5-40.5), and 0.018 g cm −3 (0.68-0.85) for the mass, apparent volume, and bulk density, respectively.

An investigation dedicated to evaluating a big issue in biorefineries, solid impurity in raw sugarcane, is presented. This relevant industrial sector requests a high-frequency, low-cost, and noninvasive method. Then, the developed method uses the averaged color values of ten color-scale descriptors: R (red), G (green), B (blue), their relative colors (r, g, and b), H (hue), S (saturation), V (value) and L (luminosity) from digital images acquired from 146 solid mixtures among sugarcane stalks and solid impurity � vegetal parts (green and dry leaves) and soil. The solid mixture of samples was prepared considering desirable and undesirable scenarios for the solid impurity amounts. The outstanding result was revealed by an artificial neural network (ANN), achieving 100% of accurate classifications for two ranges of raw sugarcane in the samples: from 90 to 100 wt% and from 41 to 87 wt%. Low-computational cost and a simple setup for image acquisition method could screen solid impurity in sugarcane shipments as a promising application.