ПРИМЕНЕНИЕ МЕТОДА ЦВЕТОВОЙ СЕГМЕНТАЦИИ В ЗАДАЧЕ ОПРЕДЕЛЕНИЯ ОДНОРОДНОСТИ КОРМОСМЕСИ

Abstract

The prepared compound feed’s quality by the resulting mixture uniformity is assessed. The known methods for this indicator determining by the control component or mixture components’ electrophysical properties involve sampling analysis, that is resource expensive and ineffective. The machine vision using for mixing quality in real time determining is more efficient way. However, the feed mixture is blurred bulk media by its characteristics, that makes it difficult photo and video recording to mixture’s composition study carrying out. This study peculiarity is that the mixture’s mixing quality by machine vision methods using to analyze of images obtained blurred bulk media using by an endoscope with an annular illuminator is determined. The endoscope is mounted in a cylindrical protective box with a transparent end glass (the optical axis of the endoscope and the cylinder’s axis are coincided). To analyze each image, a binary mask highlighting only the image’s informative part is constructed it means that image’s part from which the highlights from the annular illuminator and the protective box’s glass outside area are excluded. Next, these colors’ average values of the template image corresponding to the recognized mixture components are calculated, then the number of pixels closest to Euclidean metric to selected color clusters corresponding to the number of mixture’s components is determined. The color’s numerical characteristic by the RGB channels or Lab color representations is set. The paper shows that in the case of a multicomponent mixture working the Lab space gives better results in compared to the RGB space. The estimation of the color segmentation method’s error determining the number of pixels corresponding to a particular color’s cluster is given. It is shown that the morphological operation of image’s connected areas removing reduces the number of "false" pixels in the color cluster. In the future, the obtained results in the feed components uniformity distribution’s program determining will be included.