Automatic Phenotyping Test of Sunflower Seeds

Abstract The development of automated precision technologies for the phenotyping test of seeds by a complex of functional features in the selection process of sunflower is relevant and promising. The task of developing a device for the automatic phenotyping test of seeds and the algorithm for finding and isolating seeds based on color information was set. Research was conducted on a stand, which consisted of the following elements: Video Microscope Camera 1080 P 16MP HDMI USB manufactured by Eakins, a set of LEDs of three types (red, green, blue) and a personal computer. The results of experimental studies of the process of automatic phenotyping test of seeds of different sunflower varieties allowed us to establish an average error of determining the geometric dimensions of sunflower seeds (length L and width B) – 0.06 mm. The histograms of the color distribution of sunflower seeds in the RGB color space with different illumination are established. As a result of the analysis of the obtained histograms of the color distribution of sunflower seeds in the RGB color space it is established that in the case of color homogeneity, the discreteness of the channels with red illumination is most clearly seen. A device for automatic phenotyping test of seeds has been developed, which preserves the accuracy of individual measurement of the geometric dimensions of sunflower seeds, determining their shape and color, which corresponds to modern measuring tools, and provides low complexity and high technological implementation of the phenotyping test procedure (determination, ascertaining and identification) material, according to its morphological and marker features.