Optimization of Machine Vision for Tomato Grafting Robot

Department of Farm Power and Machinery, Bangladesh Agricultural University, Mymensingh-2202, Bangladesh(Received: 20 March 2012. Accepted: 10 October 2012)In order to develop fully-automatic grafting robot for tomato seedlings, the machine vision system forsorting grafting seedling and inspecting grafted seedling was studied. In this paper, the devices anddifferent lighting (Front lighting, Backlight, and both Front lighting and Backlight) of machine visionsystem were optimized and selected. The result shows that Blue Backlight without filter device isbest for both sorting and inspecting seedlings. Then the images of sorting and inspecting seedlingswere acquired using the selected machine vision system and processed by the program. Experimentresults show the success rate on processing the images of sorting seedlings can reach 96% andeven the gap of 0.2 mm between scion and rootstock can be found easily when inspecting graftedseedling.