A 3D machine vision system for quality grading of Atlantic salmon

Abstract

Quality grading of Atlantic salmon (Salmo salar) is currently a task performed manually by human operators. To stay competitive in an increasingly global market, it becomes necessary to take advantage of technology to improve productivity and profitability. The Norwegian salmon industry sees the need to automate quality grading, in order to reduce tedious manual labor and to increase product consistency and production flexibility. A machine vision system for external 3D imaging in color, with a 360° scanning cross-section, has been developed for the purpose of quality grading of Atlantic salmon. The two primary causes of downgraded salmon are deformities and wounds. Two classifiers were developed, based on 3D geometric features and color information, to handle each of these primary causes of downgrading. These classifiers are able to detect deformities and wounds, with discrimination efficiencies of 86% and 89% respectively. This work shows that 3D machine vision can enable real-time automatic quality grading of Atlantic salmon. Many of the methods employed are general enough to translate to other species of fish or similar applications with minor modifications.