<h1 align="center">NanoNets ID Card Digitization Sample</h1>

Extracting Information From ID Cards

Annotations include bounding boxes for each image and have the same name as the image name. You can find the example to train a model in python, by updating the api-key and model id in corresponding file. There is also a pre-processed json annotations folder that are ready payload for nanonets API.

Build an ID Card Info Extraction Model

Note: Make sure you have python and pip installed on your system if you don't visit
Python,
pip

Step 1: Clone the Repo, Install dependencies

git clone https://github.com/NanoNets/nanonets-id-card-digitization.git
cd nanonets-id-card-digitization
sudo pip install nanonets

Step 2: Get your free API Key

Get your free API Key from http://app.nanonets.com/#/keys

Step 3: Set the API key as an Environment Variable

export NANONETS_API_KEY=YOUR_API_KEY_GOES_HERE

Step 4: Upload Images For Training

The training data is found in images (image files) and annotations (annotations for the image files)

python ./code/training.py

_Note: This generates a MODEL_ID that you need for the next step

Step 5: Add Model Id as Environment Variable

export NANONETS_MODEL_ID=YOUR_MODEL_ID

_Note: you will get YOUR_MODEL_ID from the previous step

Step 6: Get Model State

The model takes ~2 hours to train. You will get an email once the model is trained. In the meanwhile you check the state of the model

python ./code/model-state.py

Step 7: Make Prediction

Once the model is trained. You can make predictions using the model

python ./code/prediction.py PATH_TO_YOUR_IMAGE.jpg

Sample Usage:

python ./code/prediction.py ./images/111.jpg

Note the python sample uses the converted json instead of the xml payload for convenience purposes, hence it has no dependencies.