kuwachi

Great idea on building it into a case!

The mayoclinic does a really great job, but from our outreach at health fairs, people seem to have so many problems with portion control.

We had one batch of spaghetti pasta out, and we asked people how many ounces it was (it was 4 - double the portion). Only about 2% of the population got the answer right.

However I give you mega props for knowing portion control!

hmm.. never.. thought.. about.. the alternative.. uses..

So here is the logic in terms of the employer (company owner). Generally speaking, employers want their employees to be healthier so they use less pto, less health care, and to be more productive.

I think there are already some other apps where users can self report their fitness and get rewards through their respective company.

So the ultimate goal of the app is to get people to eat healthier. There are obviously many angles to this such as portion control, fiber intake, and meat, vegetables, and fruits ratio.

As to what constitutes 'healthy', it is pretty controversial, where if you ask 2 doctors, you'll get pretty much 3 answers.

Generally speaking our behavior goals for the user is to add more fruits, vegetables, and fiber specifically. When speaking with UCLA's head of oncology she pointed out that academic literature points out to most people lacking this in their diet and that consuming those items would lead to improved health.

Now as a previous commenter about overeating, at the very least the apple contains 12% fiber and 10% of vitamin C you need daily.

App link for background information: http://www.foodsnap.mobi

As you can imagine, the problem of getting nutrition information from food is a really difficult problem, so we are breaking it into chunks.

For our first phase, we are using user input to provide a baseline of nutrition information. Some people don't want to use the existing apps which require you to select an item from an auto dropdown, then select the quantity.

For our second phase however, we are doing what you said. With the image and input data, we are training our artificial intelligence system to see if it can fix user entries, or at least provide a 'guess' of ingredients for the user.

Some interesting solutions we have seen from Harvard research papers is to get an image, then generate vector image shapes. With the image shapes, we can access portion size + the caption and fix that.