Translating food images into nutrient information

The prevention of both onset and progression of diet-related acute and chronic diseases (e.g. diabetes, obesity, kidney disease) requires reliable and intuitive systems able to translate food intake into nutrient intake.

Since 2008, researchers of the ARTORG Center of the University of Bern are developing technologies that harness the synergy of artificial intelligence and computer vision to make the dietary assessment real-time, accurate and more cost efficient than the conventional methods. Here, basic, applied and translational research allows to bridge the gap between science and practice at both clinical and real-life settings. The translation of the technologies to benefits for the persons is of eminent importance for the group. Diabetes and hospitalised malnutrition are cases in which the analysis of simple meal photos allows to decrypt information related to the nutrient content of the meal.

Our interdisciplinary team analyses the needs, shapes the technology to meet real challenges and provides users with actionable data related to dietary assessment.