AadhaarAdmin Scope

The AADHAAR model is a part of the Document Processing feature that enables you to process Indian Aadhaar cards as identity proof documents. This enables you to extract fields of data from an Indian Aadhaar card using an advanced OCR technology. The response will return the parameters recognized from the Aadhaar card, along with confidence scores for each recognition that determine their accuracy.

You need to provide the path to the image files of the front and back of the Aadhaar card through createReadStream. You must pass English and the relevant regional language. For example, if you are from Tamil Nadu, you must pass tam and eng as the languages.

Allowed file formats: .webp, .jpeg, .png, .bmp, .tiff, .pdf

File size limit: 15 MB

The zia reference used in the code snippets below is the component instance created to perform these operations. The promise returned here is resolved to a JSON object.

const fs = require('fs');
const result = await zia.extractAadhaarCharacters(
  fs.createReadStream('./frontImg.webp'),
  fs.createReadStream('./backImg.webp'),
  'eng,tam'
);
console.log(result);

Example of Expected Response

A sample response that you will receive is shown below. The response contains the parameters recognized in the Aadhaar card such as the card holder’s name, address, gender, Aadhaar card number assigned to respective keys. The response also shows a confidence score in the range of 0 to 1 for each of the recognized values.

{
  "text": {
    "address": {
      "prob": 0.5,
      "value": "C/O Rainbow, xxxx STREET, xxxx- 0000"
    },
    "gender": {
      "prob": 0.8,
      "value": "MALE"
    },
    "dob": {
      "prob": 0.8,
      "value": "08/09/2001"
    },
    "name": {
      "prob": 0.6,
      "value": "Saeyon Dheeran"
    },
    "aadhaar": {
      "prob": 0.8,
      "value": "4000 0000 0000"
    }
  }
}