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...

Full description

Saved in:
Bibliographic Details
Published in:Journal of intelligent & fuzzy systems 2018-01, Vol.35 (2), p.1511-1518
Main Authors: Lee, Donggil, Kim, Seonghun, Kim, Pyungkwan, Yang, Yongsu
Format: Article
Language:English
Subjects:
Algorithms
Aquatic life
Classification
Color
Harvesting
Invertebrates
Mussels
Regression analysis
Regression models
Saturation (color)
Sorting algorithms
Weight
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1064-1246
1875-8967
DOI:10.3233/JIFS-169691