Fish Identification Software Hub
- Duration: 2016-2018
- Coordinator: Istituto Zooprofilattico Sperimentale del Piemonte Liguria e Valle d’Aosta
- Partners: Istituto Zooprofilattico Sperimentale del Piemonte Liguria e Valle d’Aosta, Politecnico di Torino, University of Salford
- Funded by: EU-FP7
- Project’s website: www.fishub.eu
Selling a fish species different from that declared on the label is the most frequent fraud in seafood. This fraud can have strong economical, health, and ecological implications. Currently the two most used countermeasures are visual inspection by experts and DNA analysis. Although the first method has the advantage of being performed directly at selling points, it requires experienced personnel and it heavily relies on a subjective judgement. DNA analysis, on the other hand, is a very accurate method for species identification, but it is expensive and can interfere with the production line.
Objective of the FISHUB project is to overcome the limitations of both methods by creating an objective fraud detection software usable on the field by trained personnel as well as un-experienced end users. The F.I.S.H. software will be based on image analysis and machine learning technologies, able to identify the species of a fish from its photo. The use of image recognition in food fraud is innovative because it will allow to take into account morphological features that would be extremely difficult to detect with the naked eye (e.g. colour textures, geometrical ratios between selected fish measures, relative dimensions and placement of particular fish features like fins, eye, etc…). Suspect samples identified by the software can also be sent to a laboratory for confirmation by DNA analysis, making this test more cost-effective.
To enable the widest possible use of the software, it’s access will be open and available through a mobile app designed for the most common mobile platforms.
