Photonics Spectra BioPhotonics Vision Spectra Photonics Showcase Photonics Buyers' Guide Photonics Handbook Photonics Dictionary Newsletters Bookstore
Latest News Latest Products Features All Things Photonics Podcast
Marketplace Supplier Search Product Search Career Center
Webinars Photonics Media Virtual Events Industry Events Calendar
White Papers Videos Contribute an Article Suggest a Webinar Submit a Press Release Subscribe Advertise Become a Member


Vision System Helps Correct Herring Problems

Daniel C. McCarthy

They may be fish eggs to you, but each year Japanese sushi bars hatch a market that averages more than $100 million just for herring roe fished from the coastal waters off both British Columbia, Canada, and Alaska. This delicacy, called kazanoko, arrives at the table as a firm mass of salty eggs. It can land wholesale prices as high as $15 per pound. Epicureans willing to shell out for the cost of a single serving expect kazanoko to appear on the plate in perfect condition and with impeccable taste and texture. Thus, quality control starts early in the processing operation. One machinery manufacturer, Neptune Dynamics Ltd., opted for an integrated inspection system from Sharp Digital Information Products.

Neptune's processing machinery is designed to separate roe from fish at rates of 300 units per minute. Like earlier systems, the newest machine separates the fish into pockets along the processing belt. But much of the work once performed by five human operators has been automated in the new system to speed output, said Richard Green, Neptune's president. To do this properly, the system needs to identify which way each fish is facing so it extracts the mass of eggs without damaging them. "Roe that can sell for $15 a pound drops to $2 a pound if the roe is cut improperly," Green said.

A human operator still ensures that each pocket packs a single fish, but once loaded, the fish move along the belt too rapidly to allow an operator to correct their position. Instead, Sharp's progressive-scan camera monitors the belt and feeds information to computer boards and software from Neptune that trigger an error actuator to correct backward fish. The system is programmed to distinguish a white fish belly from white light reflecting off the wet black back of the fish.

"It's not a pristine situation where you have individual fish taken out of the ocean and laid in the bottom of a tackle box. This is an industrial application; they've been handled mechanically. The program can't be confused by flaws in the fish," Green said.

"The environment is wet, and we didn't want the hassles of trying to package a full computer into this environment, which is why the small size of the Sharp system was convenient," he added.

Explore related content from Photonics Media




LATEST NEWS

Terms & Conditions Privacy Policy About Us Contact Us

©2024 Photonics Media