Fish Inspection System Using a Parallel Neural Network

A generic image learning system, CogniSight®, is being used for the inspection of fishes before filleting off-shore. More than thirty systems have been deployed on seven fishing vessels in Norway and Iceland over the past three years. Each CogniSight uses four neural net-work chips (a total of 312 neurons) based on a natively parallel hardwired architecture performing real time learning and non-linear classification (RBF). These sys-tems are trained by the ship crew using Image Knowl-edge Builder, a ”show and tell ” interface for easy train-ing and validation. Fishermen can reinforce the learning at anytime when needed. The use of CogniSight has re-duced significantly the number of crewmembers on the boats (by up to six persons) and the time at sea has shortened by 15%. The prompt and strong return of the investment to the fishing fleet has increased signifi-cantly the market shares of Pisces Industries, the com-pany integrating CogniSight systems to its filleting ma-chines