Automatic sea squirt sorting algorithm based on the HSV color model and weight estimation

Sea squirts are cultivated mainly in Korea, Japan, and China. Sea squirt sorting during the harvesting process is labor-intensive and time-consuming as there is no automatic sorting technology for sea squirts. In this study, we developed and evaluated an automatic sea squirt sorting algorithm based on sea squirt color information analyzed using the hue-saturation-value (HSV) color model and the regression equation of the projected area and weight of the sea squirt. The developed algorithm recognizes sea squirts during the sorting process based on the threshold range of sea squirt color values and their weight based on measurements of the projected area. In 100 repeated experiments conducted with mixed products containing sea squirts, mussels, and Styela clava, the average sea squirt recognition rate of the developed algorithm was 98.5%, and the sorting performance based on animal weight and grade was ≥95.5% at an average speed of 1,050 kg/h.