fresh bytes
Subscribe Now

AI demo picks out recipes from food photos

An algorithm created to identify recipes for food just from a photograph has been demonstrated by researchers at the Massachusetts Institute of Technology (MIT).

The neural network was trained on a dataset of one million photos and one million recipes.

The trial model worked best on desserts and found smoothies and sushi more challenging, the researchers said.

The team has released an online trial although it is not a finished product.

When tested by the BBC, recipes that were generated based on a picture of spaghetti bolognese included “Italian tomato sauce” and “gunk on noodles”.

Continue reading at BBC News

Leave a Reply

featured blogs
Feb 21, 2019
The Cadence® Quantus Smart View is the next generation of the Extracted View in the Virtuoso environment. The Smart View provides the same functionality as the Extracted View, but it uses a... [[ Click on the title to access the full blog on the Cadence Community site. ...
Feb 21, 2019
Embedded World 2019 is the conference for security in electronic systems, distributed intelligence, the Internet of Things / e-mobility, and energy efficiency. In other words, you are going to experience a wide range of embedded systems. It shouldn’t come as a surprise,...
Feb 19, 2019
Recognized for contributions to Verilog, SystemVerilog, UVM and Portable Stimulus Accellera has selected our own Tom Fitzpatrick as its 2019 Technical Excellence Award honoree '€“ and the first Mentor employee to ever receive this prestigious recognition. From all of us at ...
Jan 25, 2019
Let'€™s face it: We'€™re addicted to SRAM. It'€™s big, it'€™s power-hungry, but it'€™s fast. And no matter how much we complain about it, we still use it. Because we don'€™t have anything better in the mainstream yet. We'€™ve looked at attempts to improve conven...