The article examines the main stages in the development of a statistical method for localizing and classifying grain crop defects in conditions of low resource consumption of hardware and software of modern agricultural sorting systems. The developed methodology allows: to form a set of coefficients that make it possible to quantify the area under study; the use of the variation coefficient enables to unambiguously assess the homogeneity of the contents of the investigated area; the analysis of the obtained groups of variation coefficients provides for localization of the alleged defect against the general background of the contour, with its contents heterogeneity.
The paper proposes an automated procedure for assessing the actual state of photoelectronic separators in real time. Random process outliers over tolerance zones are proposed as the main controlled parameter. In contrast to traditional methods, several threshold levels are used to provide the flexibility of control and forecasting. Measurement of the amplitude and duration of the outliers of random processes over the tolerance zones helps to collect statistical samples, which become the basis for statistical models in the form of distribution law. The automated system makes it possible to identify the distribution law by classical methods if the samples are of sufficient statistical volume.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.