Image processing algorithms in the assessment of grain damage degree

Abstract

Objectives: The paper presents preliminary results on the assessment of algorithms used in image processing of the grain damage degree. The purpose of the work is developing a tool allowing to analyse sample cross-sections of rye germs. Methods: The analysis of the grain cross-sections was carried out on the basis of a series their photos taken at equal time intervals at a set depth. The cross-sections will be used to create additional virtual cross-sections allowing to analyse the whole sample volume. The ultimate plan is to generate two cross-sections perpendicular to each other. Based on volumetric data read from the sample section, a three-dimensional model of an object will be generated. Results: The analysis of model surface will allowed us to detect possible grain damage. The developed method of preparing the research material and the proprietary application allowed for the identification of internal defects in the biological material (cereal grains). Conclusions: The presented methodology may be used in the agri-food industry in the future. However, much research remains to be done. These works should primarily aim at significantly reducing the time-consuming nature of individual stages, as well as improving the quality of the reconstructed image.