Experts suggest that analyzing food pictures, that are widely and easily available on social media, can help understand people's eating habits and dietary preferences. Given a photo of a food item, 'Pic2Recipe' could identify ingredients like flour, eggs and butter, and then suggest several recipes that it determined to be similar to images from the database.
"You can imagine people using this to track their daily nutrition, or to photograph their meal at a restaurant and know what's needed to cook it at home later," said Christoph Trattner, assistant professor at MODUL University Vienna who was not involved in the study.
While experts faced difficulty in determining ingredients for more complex food items like sushi rolls, doing the same for foods like cookies and other desserts was comparatively easier. The team suggested working more on the system to be able to derive more elaborate and in-depth information about various eatables. The system can be seen as a vital tool in collecting a pool of food images from social media and arriving at the broader picture of what people eat on a day-to-day basis and how healthy their dietary choices actually are. If possible, the system could also suggest healthier substitutes for creating the same recipe.
Inputs from IANS
