Logo of the Information System for Agriculture and Food Research

Information System for Agriculture and Food Research

Information platform of the Federal and State Governments

Collaborative project: Development of automated analysis techniques for the identification and assessment of non-compliant products of the virtual food market place ' (AAPVL)

Project


Project code: 2819102112
Contract period: 15.02.2013 - 14.02.2016
Budget: 484,126 Euro
Purpose of research: Experimental development

Regulation (EC) No 882/2004 postulates the inclusion of the virtual food market into the official food control system. However, there is currently no automated IT-based solution for the identification of potentially non-compliant products of the virtual food market place available. Non-compliant food products are often classified as unlicensed drugs that are commercialized as dietary supplements which may contain hazardous ingredients. Furthermore those products frequently bear scientifically not proven health claims or may contain unapproved food ingredients (Novel foods) or food additives. At present searches for potentially non-compliant products of the virtual food market must be performed manually with high expenditure of time and effort. Therefore the aim of this research project is to develop a system for the automatic identification of potentially non-compliant foods including the compilation of relevant vendor information. The research project will contribute to increase consumer health protection and food safety with respect to foods commercialized via the internet. This aim will be achieved especially by: + the development of a monitoring component for a regular automated search for specific foods / ingredients + the development of a prototype for (semi-) automatic jurors based assessment of potentially non-compliant foods + the adaptation and integration of text, pattern and image recognition techniques for the identification of non-compliant food under consideration of specific claims Within the project an IT-based prototype will be developed which is based on the structure of an existing Relevance Assessment Tool (RAT) developed by Hamburg University of Applied Sciences (HAW Hamburg). The text, pattern and image recognition will arise from further development of external software solutions and will be accessed via appropriate interfaces to the prototype. The project partner, the Federal Office of Consumer Protection and Food Safety (BVL), is significantly involved in all stages of development, particularly in assessing the practicality of the developed prototype.

show more show less

Subjects

Excutive institution

Department of Nutrition (OET)

Advanced Search