When Spectre, Hectre’s fruit sizing technology was launched, it didn’t take long before fruit warehouses began the push for colour. They told us that with colour estimation through a tool like Spectre, they could better assess fit for market, store more efficiently, and most importantly, sell the right fruit at the right time.

So the Hectre team did what the Hectre team do – they took the problem and they solved it.

Reading colour can be subjective, so computers need to be taught using computer vision and AI. This created the major work stream for the Spectre for Colour project team. For those unfamiliar with computer vision, it’s a science which focuses on replicating parts of the complexity of the human vision system, enabling computers to identify and process objects in images in the same way that humans do. At Hectre, we’re extremely fortunate to have some amazing talents in the computer vision field.

A quick and simple to use, two step calibration process was then designed whereby warehouse supervisors are able to set up and save standard settings such as “Inside with lighting”, “Sunny outdoors” and so on, and then simply calibrate the colour for that setting.

These settings reflect the difference environments make on viewing colour and lets Spectre know to adjust for those environments.

Once saved, settings can be selected at any time by any user, and new settings can be added.