Document Type : Original Article
Authors
Assistant Professor, Agricultural Engineering Research Department, Fars Agricultural and Natural Resources Research and Education Center, Agricultural Research Education And Extention Organization, Shiraz, Iran
Abstract
In this research, a machine vision system was used and evaluated for seeds of sorghum, cotton and barley. For each type of seed, the performance of the suction device, with three seed plates (with hole diameters of 1, 1.5 and 2 mm) and four suction values (-80, -100, -120 and -130 mmHg) was evaluated. In each f suction value, the total number of seeds sticked to the seed plate, the number of singled seeds and the number of sticked seeds on each hole were counted and their percentage was calculated. After that, for the three types of seeds tested, the algorithm for determining the percentage of breakage and the number of seed coding and validation of the algorithm was evaluated in 30 repetitions. The results showed that for sorghum seed, treatment No.1 (seed plate with 1 mm holes and suction value of -80 mm Hg), for cotton seed, treatment No. 5 (seed plate with 1.5 mm holes and suction value of -80 mm Hg), and for barley seed, treatment No. 2 (seed plate with 1 mm holes and suction value of -100 mm Hg), were the most suitable treatments. The validation results of the algorithm for determining the percentage of breakage and the number of seeds for the three types of seeds tested showed that the average accuracy of the algorithm was equal to 100%.
Keywords
)