Marriage Certificate OCR

This article walks you through the building process of an OCR API that extracts data from Marriage Certificates using our deep learning engine. It will work for any bank company or bank statement template.


  1. You’ll need a free account. Sign up and confirm your email to login.
  2. You’ll need at least 20 Marriage Certificate images or pdfs to train your OCR.

Define your Marriage Certificate use case

First, we’re going to define what fields we want to extract from your Marriage Certificate.

Marriage certificate key data extractionMarriage certificate key data extraction

Marriage certificate key data extraction

  • Issuer Name: The name of the marriage certificate issuer
  • Issued date: The date of issue of the marriage certificate
  • Husband's Name: The husband's name
  • Wife's name: The wife's name
  • Clerk information: The clerk address information

That’s it for our use case. 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 ‘Create a new API’ button.

You land now on the setup page. Here is the image you can use to set up the API. For instance, my setup is as follows:
Set up your modelSet up your model

Set up your model

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

Define your modelDefine your model

Define your model

To move forward, you have two possibilities:

Upload a json config
Copy the following JSON into a file and upload it on the interface

  "problem_type": {
    "classificator": { "features": [], "features_name": [] },
    "selector": {
      "features": [
          "cfg": { "filter": { "alpha": -1, "numeric": 0 } },
          "handwritten": false,
          "name": "issuer_name",
          "public_name": "Issuer Name",
          "semantics": "word"
          "cfg": { "filter": { "convention": "US" } },
          "handwritten": false,
          "name": "issued_date",
          "public_name": "Issued Date",
          "semantics": "date"
          "cfg": { "filter": { "alpha": -1, "numeric": 0 } },
          "handwritten": false,
          "name": "husband_s_name",
          "public_name": "Husband's Name",
          "semantics": "word"
          "cfg": { "filter": { "alpha": -1, "numeric": 0 } },
          "handwritten": false,
          "name": "wife_s_name",
          "public_name": "Wife's name",
          "semantics": "word"
          "cfg": { "filter": { "alpha": -1, "numeric": 0 } },
          "handwritten": false,
          "name": "clerk_information",
          "public_name": "Clerk Information",
          "semantics": "word"
      "features_name": [

Or build your data model manually
Using the interface, add up to your data model each field.

In our example, here are the different field configurations we used:

  • Issuer Name: type String that never contains numeric characters.
  • Issued Date: type Date with US format.
  • Husband's Name: type String that never contains numeric characters.
  • Wife's name: type String that never contains numeric characters.
  • Clerk Information: type String that never contains numeric characters.

Once you’re done setting up your data model, press the Start training your model button at the bottom of the screen.

Ready to train modelReady to train model

Ready to train model

Train your Marriage Certificate OCR

Train your modelTrain your model

Train your model

You’re all set!

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

In a few hours (minutes if you're fast), you’ll get your first model trained and will be able to use your custom OCR API for parsing Marriage Certificate in your application.

To get more information about the training phase, please refer to the Getting Started tutorial. If you have any question regarding your use case, feel free to reach out on our chat!

Updated 8 months ago

Marriage Certificate OCR

Suggested Edits are limited on API Reference Pages

You can only suggest edits to Markdown body content, but not to the API spec.