THE APPLICATION

• Sort fishes on a boat before they enter the filleting machine at 360 ppm.
• Accept, Reject or Recycle based on the species, the fish conditions and its orientation in the metal pocket

THE CHALLENGE

• Typical case of non-linearity where it is impossible to model mathematically all the possible variations of the fishes.
• Fish scales are highly reflective
• The size and scales of a same species of fishes can vary depending on the season and the location of the catch.
• The system must be compact, waterproof and require zero maintenance while running 24 hrs/day during sea expeditions
• The interface must be very simple to operate: a “boxing-glove” type keypad which the fishermen can use to setup and teach the camera themselves

THE SOLUTION

• More than a dozen boats equipped by Pisces Industries with cameras featuring CogniMem neurons.
• The camera recognizes acceptable herrings passing on the conveyor belt and activates if necessary the rejection and recycling brushes.
• Training was done on approximately 3000 images, accumulated during several expeditions. It can be saved and transferred to cameras installed on other boats.
• Final recognition engine of approximately 100 neurons and accuracy of 98%.