More and more fish are being farmed in controlled conditions, which increases the need for knowledge about breeding conditions, animal health and quality, according to Wageningen University & Research (WUR) in the Netherlands.
WUR said its Greenhouse Horticulture Business Unit is working on methods to select fish automatically, quickly and accurately.
AquaIMPACT is a European project with partners from different countries, including Wageningen Plant Research and Wageningen Livestock Research. Together, they are investigating the professional breeding of Atlantic salmon, rainbow trout, golden bream and sea bass, WUR said. The Greenhouse Horticulture Business Unit is responsible for developing "machine vision" and "machine learning" to analyze the fish.
Machine vision is a collective name for techniques for editing and/or analyzing camera images, WUR explained. The use of vision techniques has many advantages, including that more variables can be measured in a shorter time, and software is more objective than human observers.
WUR said it has much experience with applying vision techniques, such as phenotyping (measuring plant properties with cameras and software). The shape and color characteristics of farmed fish must also be assessed, which allows a breeder to decide which fish will be used for further breeding -- a practice currently being done by hand, WUR said.
WUR is developing a device with a company for measuring the assorted variables of the fish, such as the shape, color and body parts like eyes or belly. The fish are then removed from the breeding tank.
An algorithm — developed by the Greenhouse Horticulture Business Unit — compares the characteristics of the fish with genetic information from a database. The device then sorts the fish. The entire operation is completed in approximately 30 seconds. As a result, the fish has as little stress as possible, WUR reported.