Nutrition Facts label OCR

 

This article walks you through the building process of an OCR API that extracts data from Nutrition Facts labels using our deep learning engine. It will work for any food brand or label template. 

 

 

Prerequisites

  1. You’ll need a free beta account. Sign up and confirm your email to login.
  2. You’ll need at least 20 nutrition facts labels or pdfs to train your OCR.

 

 

Define your Nutrition fact label use case

 

First, we’re going to define what fields we want to extract from your Nutrition fact label. 

 

 

Nutrition Facts label OCR

 

  • Serving size: 170 gram 

 

  • total fat gram: 2 gram

 

  • total fat daily value : 3%

 

  • calories per serving: 150

 

 

That’s it for our use case. Remember this is an example feel free to add any other relevant data to fit your requirements.

 

 

Deploy your API

 

Once you have defined the list of fields you want to extract, head over to the platform and press the ‘build a new endpoint’ button.

 

You land now on the setup page. Here is the image you can use for setting up the API, and my setup looks like this:

 

 

Setup your nutrition facts label OCR API”

 

 

Once you’re ready, click on the “next step” button. We are going to specify the data types for each of the fields we want our API to extract.


 

To go further, you can download this json config to set up your data model or do it manually.


 

Serving size: type Integer 

 

serving size field for nutrition facts label OCR

 

 

 

Total fat gram: type Number

 

Total fat gram field for nutrition facts label OCR

 

Total fat daily value: type String that never contains alpha characters

 

Total fat daily value field for nutrition facts label OCR

 

Calories per serving: type Integer

 

Calories per serving field for nutrition facts label OCR

 

 

 

 

Once you’re done setting up your data model, press the Data model ready? start training button at the top of the screen.

 

 

Train your Nutrition facts labels OCR

 

 

Nutrition facts label OCR API training

 

 

You’re all set! 

 

Now is the time to train your nutrition facts to train deep learning model in the Training section of our API. 

 

In a few minutes, you’ll get to this point :

 

 

 

Your first model is trained you're now able to use your custom OCR API for parsing nutrition facts labels in your application.

 

 

To get more information about the training phase, please refer to the getting started tutorial. If you have any questions regarding your use case, feel free to reach out!