Introduction

Identity recognition is a technology or process that involves the automatic identification and interpretation of structured information from various types of identity documents. It typically utilizes computer software and often incorporates techniques like Optical Character Recognition (OCR) and pattern recognition to analyze and extract data from printed or digital documents. Here’s a more detailed explanation of what forms recognition is and its key aspects:

• Document Types: Identity recognition can be applied to a wide range of identification documents, and more.

• Data Extraction: The primary goal of forms recognition is to extract specific data elements from these documents. This data can include text, numbers, dates, checkboxes, and other structured information. The extracted data can be further processed, stored, or used for various purposes.

• Optical Character Recognition (OCR): OCR technology plays a crucial role in forms recognition, especially when dealing with printed or handwritten text. OCR software converts text from scanned images or handwritten documents into machine-readable text, making it easier for computers to analyze and extract information.

• Automation: Forms recognition is often used to automate data entry and processing. Once data is extracted, it can be automatically integrated into databases, information systems, or business processes, reducing the need for manual data entry and minimizing errors.

• Identity recognition is a valuable tool for organizations looking to streamline data capture, improve data accuracy, and enhance document management processes. It has the potential to save time and resources while increasing the overall efficiency of various business operations that involve handling structured documents.

API Endpoints

/id

Description

Return metadata formatted as JSON. Key/value paris are identified. Each unit will include:

• Identifiers - collection of data identified and extracted fromthe document. This will include for each
  • Confidence = level of confidence from 0 to 100
  • Type = Type of data identified
  • Value = OCR text

Request

The body of the request contains the binary data of the image to be processed. The binary data can be represented as:

• Straight binary data
• Data Url Schema (https://datatracker.ietf.org/doc/html/rfc2397)
• Mulipart Form Data - first file is used (https://datatracker.ietf.org/doc/html/rfc1867)

Example

{
    "Identifiers": [
        {
            "Type": "FIRST_NAME",
            "Value": "THOMAS",
            "Confidence": 96.57107543945312
        },
        {
            "Type": "LAST_NAME",
            "Value": "ARMSTRONG",
            "Confidence": 98.95633697509766
        },
        ...
        {
            "Type": "DATE_OF_BIRTH",
            "Value": "10/01/1980",
            "Confidence": 97.34353637695312
        },
    ]
}

/id/text

Description

Return metadata formatted as JSON. Key/value paris are identified and listed in an Identifier list. Also, all text identified will be listed in a TextValue section. The metadata will include:

• Identifiers
  • Confidence = level of confidence from 0 to 100
  • Type = Type of data identified
  • Value = OCR text
• TextValues
  • Confidence = level of confidence from 0 to 100
  • Text = OCR text (single word)
  • BoundingBox
    • Height = height of the bounding box as a ratio of the overall document page dimension
    • Left = X-coordinate, ratios of the overall document page size
    • Top = Y-coordinate, ratios of the overall document page size
    • Width = width of the bounding box as a ratio of the overall document page dimension

For example, if the input image is 700 x 200 pixels, and the top-left coordinate of the bounding box is 350 x 50 pixels, the API returns a left value of 0.5 (350/700) and a top value of 0.25 (50/200). The upper-left corner of the image is the origin (0,0).

Request

The body of the request contains the binary data of the image to be processed. The binary data can be represented as:

• Straight binary data
• Data Url Schema (https://datatracker.ietf.org/doc/html/rfc2397)
• Mulipart Form Data - first file is used (https://datatracker.ietf.org/doc/html/rfc1867)

Example

{
    "Identifiers": [
        {
            "Type": "FIRST_NAME",
            "Value": "THOMAS",
            "Confidence": 96.57107543945312
        },
        {
            "Type": "LAST_NAME",
            "Value": "ARMSTRONG",
            "Confidence": 98.95633697509766
        },
        ...
        {
            "Type": "DATE_OF_BIRTH",
            "Value": "10/01/1980",
            "Confidence": 97.34353637695312
        },
    ]
    "TextValues": [
        {
            "Confidence": 44.86408233642578,
            "Text": "IDAHO®",
            "BoundingBox": {
                "Height": 0.13554219901561737,
                "Left": 0.02619503065943718,
                "Top": 0.036299046128988266,
                "Width": 0.31958794593811035
            }
        },
        ...
        {
            "Confidence": 99.9381103515625,
            "Text": "VETERAN",
            "BoundingBox": {
                "Height": 0.043353673070669174,
                "Left": 0.6289162039756775,
                "Top": 0.9401019811630249,
                "Width": 0.1575053483247757
            }
        }
    ]
}

Types lookup table

First Name — FIRST_NAME
Last Name — LAST_NAME
Middle Name — MIDDLE_NAME
Suffix — SUFFIX
City in Address — CITY_IN_ADDRESS
Zip Code In Address — ZIP_CODE_IN_ADDRESS
State In Address — STATE_IN_ADDRESS
County — COUNTY
Document Number — DOCUMENT_NUMBER
Expiration Date — EXPIRATION_DATE
Date of Birth — DATE_OF_BIRTH
State Name — STATE_NAME
Date of Issue — DATE_OF_ISSUE
Class — CLASS
Restrictions — RESTRICTIONS
Endorsements — ENDORSEMENTS
Id Type — ID_TYPE
Veteran — VETERAN
Address — ADDRESS