Vision system grades eggs

Researchers from the University of Kuala Lumpur (Kuala Lumpur, Malaysia) have developed a prototype image processing system to classify commercial eggs into their respective grades.

The first step in the process involved capturing images of 120 eggs -- 20 eggs from each of six grades from AA to E. These were then classified into a database based on the number of white pixels in the images of the eggs.

Software developed in MATLAB from The MathWorks (Natick, MA, USA) then classified eggs as they moved along a conveyor under the imaging system by comparing the number of white pixels in the images of the eggs with those stored in the database.

Experimental results demonstrated that the system was able to classify the sample of commercial eggs into their respective grades with an accuracy of 80 percent to 90 percent.

The image processing software also measured the cleanliness of the eggs in parallel with the egg grade classification process.

Details of the system, which were published in the Proceedings of the World Congress on Engineering 2012, are available on-line here.

-- Dave Wilson, Senior Editor, Vision Systems Design