Artificial vision focuses on potatoes

In the past six months, ComputerVision has made headlines for its work in the agricultural industry: first with oranges, then with strawberries, and now with potatoes.

In collaboration with the British Potato Council, the Centre for Vision and Robotics Research at the University of Lincoln has created a machine that is able to detect defective potatoes.


Image courtesy of the USDA

Currently, standard potato protocol requires that they’re sorted and classified by people, who have nothing to rely on except for their eyes and their hands. This new system will work by calling upon information supplied to it from sample batches of bad potatoes, and has the ability to store information and learn from it.

The potato prototype was made from what are known as “off-the-shelf” materials. Essentially, there weren’t any kind of special parts that were ordered for its construction, which demonstrates just how much can be accomplished with few materials and little money. Naturally, the team is convinced that more expensive and specialized hardware could result in an even better model in the future.

Leave a Reply

Post Navigation