Communications of the ACM
'Nutty' Professors Develop Machine Vision Almond Grading Machine
The prototype almond grading and contaminant detection machine has been field tested at Riverland Almonds.
Credit: University of South Australia
Researchers at the University of South Australia, in conjunction with industry partner SureNut, have developed a machine that dramatically improves the accuracy of grading almonds, which Australia exports to 50 other nations.
Funded through the Cooperative Research Centres Projects program, the research team combined cameras and purpose developed AI algorithms to create a system that can examine almond quality in greater detail than the traditional manual process, which is slow, labor intensive, and subjective.
"This machine can detect defects more quickly and more accurately than manual grading, and by using two high definition cameras and a transparent viewing surface, it can also view both sides of the nut simultaneously," says team leader Associate Professor Sang-Heon Lee.
The system uses a hyperspectral camera for contamination detection. "We also discovered some new information about hyperspectral imaging in general, which we will share with the wider research community in time," says researcher Wilmer Ariza.
From University of South Australia
View Full Article
No entries found