Robotic solutions for the handling of food products have been notably absent from suppliers’ catalogues and indeed from research laboratories. This is primarily due to the peculiarities that handling food adds to the general pick‐and‐place task. These are the complexity of handling non‐rigid products that are infinitely variable in shape, the hygiene requirement which stipulates IP65 or better for the hose‐down environment, and the reality that the food industry produces low margin products that only make substantial profits at large volumes, whilst also requiring perfect product presentation to the consumer. In this environment, tasks which have both a short payback and other commercial advantages, such as increased operator safety or improved quality, whilst also being technically feasible, are not immediately obvious.
This paper surveys the applications of vision to fish sorting, fish fillet sorting and detection of surface and sub-surface defects (such as worms and bones). It stresses the specific implementation context, needed performances, illumination, detection principle, as well as vision algorithms. Also analyzed are the optical properties of fish. Examples of results are given.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.