Volumetric Prediction of Symmetrical-Shaped Fruits by Computer Vision
Keywords:Computer vision, Symmetrical-Shaped Fruits, Volumetric Prediction
Computer vision in the industrial sector has the highest level of need because the work is done automatically and can speed up and save time for work productivity. Not always, work will be done manually by human workers who sometimes have obstacles in the process of taking place. The high cost causes the need for technology to simplify work so it does not materialize. A simple imaging system with computer vision is proposed in this study. Measurement of volume estimates from several samples was carried out to see the efficiency of computer vision imaging work by comparing the measurement results manually and water displacement method. Computer vision imaging is built using a CMOS camera, line laser, Raspberry Pi, Python programming language, and OpenCV. Imaging results show that computer vision has the ability to read the sample volume estimate more effectively against objects that have a symmetrical shape. The smallest error percentage of measurement of volume estimation by computer vision against manual method and the water displacement was 7.44% and 7.18% for sunkist oranges and 10.88% and 13.67% for symmetrical watermelon, respectively.
Copyright (c) 2020 Science, Technology & Communication Journal
This work is licensed under a Creative Commons Attribution 4.0 International License.