At‐line monitoring of industrial corn seed classification quality by digital images analysis using smartphone

Abstract

This study aimed to evaluate the feasibility of using the PhotoMetrix PRO® application to perform the selection of good quality corn seeds from defective ones, through digital images and the multivariate analysis of color elements. An optimization of the experimental conditions was carried out. Eighteen experiments were performed varying the size of the analysis recipient, the distance of the sample from the smartphone and the size of the region of interest (ROI). A calibration model was built using a partial least squares (PLS) regression model in the determined experimental conditions, and the prediction of external samples was then performed. The conditions that provided the smallest cross-validation error consisted of using the smaller chamber, the largest ROI, and the longest distance from the smartphone to the sample. The coefficient of determination obtained by the model was .976. In addition, the root-mean-square error of calibration (RMSEC) and the root-mean-square error of cross-validation (RMSECV) obtained were 1.2% and 4.8%, respectively. In the prediction, two outliers were observed, and the RMSEP dropped to 2.2% when they were removed. The proposed methodology shows great potential to contribute to the industrial process of corn seed production. It is fast, accurate, and low cost, allowing the analysis to be performed 15 times faster than the current process. Practical Applications Corn is one of the most important commodities in Brazil's economy. During the processing of corn seeds in the industry, those of good quality are selected among the others through parameters, such as color and density, for example. The gravity table and the Color Sorter machine are equipment used for this purpose. However, even if the machine's separation is effective, an important percentage of good seeds are wasted. To reduce the waste of good seeds remaining in the tailings of these machines, the operators carry out a manual inspection of tailings samples, determining the quantity of quality seeds present there for later adjustment of the machines. This visual and manual analysis becomes time-consuming, subjective, and imprecise. Thus, as an alternative, this study proposes the use of digital image and partial least square model built by a mobile app to determine the quantity of quality corn seeds in the machines' wastes.