It often happens that you have tested a mouth-relishing dish but you were unable to guess the correct ingredients. Now put an end to this problem with the help of MIT’s new food application which is said to be in action.
The researchers at MIT have promoted a deep-learning algorithm that can merge a list of ingredients and even recommend recipes after looking at photos of food. The Artificially intelligent system still needs some fine tuning, but this tool could eventually help you learn how to cook, count calories, and track our eating habits. Researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) have taken us one step closer to get this goal but beginning to train a system to do exactly that.
Features of the Application
-The user can use the application for learning.
-The program analyzes the still images of the food and by referencing a massive database, it then predicts a list of ingredients and recommends the recipe.
-It tests, the system was able to retrieve the correct recipe around 65 percent of the time. That’s a fairly decent success rate, especially considering how complicated and varied some meals can get.
To test this application the research team led by CSAIL graduate student Nicholas Hynes collected data from websites like All Recipes and Food.com to create a database called Reciepe1M, containing over a million recipes. All the recipes were annotated with information about the ingredients found in wide variety of meal.
The Application might not able to identify all ingredients of the food in the shown image especially since there various ways to make different types food. But the application may improve in future, as the system behind the Pic2Reciepe app gets more training. The Researchers are hoping to train the system so that it can better understand that how is made (like- boiling, frying, slicing, dicing), and to tell the differences between food types (like- mushrooms and onions). They are also optimistic about to change the system into ‘dinner aide,’ where a person can key in their dietary preferences and a list of food items available in the home, and AI devices a meal based on those constraints.
Conceptually, the system should also be able to perform a calorie account, and indeed, Hynes is currently looking into this.
It’ll be a while before you see an app like this on your smartphone, but even when it does appear, a system like this will forever serve as a rough guide. Just because you know the ingredients of a meal and how it might have been put together doesn’t suddenly mean you’re a master chef.
The CSAIL team plans to present its findings later this month at the Computer Vision and Pattern Recognition conference in Honolulu.