Introducing Multi-Source Domain Adaptation for Quality Control in Retail Food Packaging

Retail food packaging contains information which informs choice and can be vital to consumer health, including product name, ingredients list, allergens, storage and shelf life information (use-by / best before dates). The presence and accuracy of such information is critical to ensure a detailed understanding of the product and to reduce the potential for health risks. In this paper, a multi-source deep learning based domain adaptation system is proposed and tested to identify and verify the presence and legibility of use-by date information from food packaging images taken as part of the validation process as the products pass along the food production line. This was achieved by improving the generalization of the techniques via incorporating new loss functions and making use of multi-source datasets in order to extract domain invariant representations for all domains and aligning distributions of all pairs of source and target domains in a common feature space, along with the class boundaries. Comprehensive experiments on our food packaging datasets demonstrate that the proposed multi-source deep domain adaptation method significantly improves the classification accuracy and
therefore has great potential for application and beneficial impact in food manufacturing control systems.