Document Intelligence business card model

Important

Starting with Document Intelligence v4.0 (preview), and going forward, the business card model (prebuilt-businessCard) is deprecated. To extract data from business card formats, use the following:

Feature version Model ID
Business card model • v3.1:2023-07-31 (GA)
• v3.0:2022-08-31 (GA)
• v2.1 (GA)
prebuilt-businessCard

This content applies to: checkmark v3.1 (GA) | Previous versions: blue-checkmark v3.0 blue-checkmark v2.1

This content applies to: checkmark v3.0 (GA) | Latest versions: purple-checkmark v3.1 | Previous version: blue-checkmark v2.1

This content applies to: checkmark v2.1

The Document Intelligence business card model combines powerful Optical Character Recognition (OCR) capabilities with deep learning models to analyze and extract data from business card images. The API analyzes printed business cards; extracts key information such as first name, surname, company name, email address, and phone number; and returns a structured JSON data representation.

Business card data extraction

Business cards are a great way to represent a business or a professional. The company logo, fonts, and background images found in business cards help promote the company branding and differentiate it from others. Applying OCR and machine-learning based techniques to automate scanning of business cards is a common image processing scenario. Enterprise systems used by sales and marketing teams typically have business card data extraction capability integration into for the benefit of their users.

Sample business card processed with Document Intelligence Studio

Screenshot of a sample business card analyzed in the Document Intelligence Studio.

Sample business processed with Document Intelligence Sample Labeling tool

Screenshot of a sample business card analyzed with the Document Intelligence Sample Labeling tool.

Development options

Document Intelligence v3.1:2023-07-31 (GA) supports the following tools, applications, and libraries:

Feature Resources Model ID
Business card model Document Intelligence Studio
REST API
C# SDK
Python SDK
Java SDK
JavaScript SDK
prebuilt-businessCard

Document Intelligence v3.0:2022-08-31 (GA) supports the following tools, applications, and libraries:

Feature Resources Model ID
Business card model Document Intelligence Studio
REST API
C# SDK
Python SDK
Java SDK
JavaScript SDK
prebuilt-businessCard

Document Intelligence v2.1 (GA) supports the following tools, applications, and libraries:

Feature Resources
Business card model Document Intelligence labeling tool
REST API
Client-library SDK
Document Intelligence Docker container

Try business card data extraction

See how data, including name, job title, address, email, and company name, is extracted from business cards. You need the following resources:

Screenshot of keys and endpoint location in the Azure portal.

Document Intelligence Studio

Note

Document Intelligence Studio is available with v3.1 and v3.0 APIs.

  1. On the Document Intelligence Studio home page, select Business cards.

  2. You can analyze the sample business card or upload your own files.

  3. Select the Run analysis button and, if necessary, configure the Analyze options :

    Screenshot of Run analysis and Analyze options buttons in the Document Intelligence Studio.

Document Intelligence Sample Labeling tool

  1. Navigate to the Document Intelligence Sample Tool.

  2. On the sample tool home page, select the Use prebuilt model to get data tile.

    Screenshot of the layout model analyze results operation.

  3. Select the Form Type to analyze from the dropdown menu.

  4. Choose a URL for the file you would like to analyze from the below options:

  5. In the Source field, select URL from the dropdown menu, paste the selected URL, and select the Fetch button.

    Screenshot of source location dropdown menu.

  6. In the Document Intelligence service endpoint field, paste the endpoint that you obtained with your Document Intelligence subscription.

  7. In the key field, paste the key you obtained from your Document Intelligence resource.

    Screenshot of the select-form-type dropdown menu.

  8. Select Run analysis. The Document Intelligence Sample Labeling tool calls the Analyze Prebuilt API and analyze the document.

  9. View the results - see the key-value pairs extracted, line items, highlighted text extracted, and tables detected.

    Screenshot of the business card model analyze results operation.

Note

The Sample Labeling tool does not support the BMP file format. This is a limitation of the tool not the Document Intelligence Service.

Input requirements

  • Supported file formats:

    Model PDF Image:
    JPEG/JPG, PNG, BMP, TIFF, HEIF
    Microsoft Office:
    Word (DOCX), Excel (XLSX), PowerPoint (PPTX), HTML
    Read
    Layout ✔ (2024-07-31-preview, 2024-02-29-preview, 2023-10-31-preview)
    General Document
    Prebuilt
    Custom extraction
    Custom classification ✔ (2024-07-31-preview, 2024-02-29-preview)
  • For best results, provide one clear photo or high-quality scan per document.

  • For PDF and TIFF, up to 2,000 pages can be processed (with a free tier subscription, only the first two pages are processed).

  • The file size for analyzing documents is 500 MB for paid (S0) tier and 4 MB for free (F0) tier.

  • Image dimensions must be between 50 pixels x 50 pixels and 10,000 pixels x 10,000 pixels.

  • If your PDFs are password-locked, you must remove the lock before submission.

  • The minimum height of the text to be extracted is 12 pixels for a 1024 x 768 pixel image. This dimension corresponds to about 8 point text at 150 dots per inch (DPI).

  • For custom model training, the maximum number of pages for training data is 500 for the custom template model and 50,000 for the custom neural model.

    • For custom extraction model training, the total size of training data is 50 MB for template model and 1 GB for the neural model.

    • For custom classification model training, the total size of training data is 1 GB with a maximum of 10,000 pages. For 2024-07-31-preview and later, the total size of training data is 2 GB with a maximum of 10,000 pages.

  • The supported file formats: JPEG, PNG, PDF, and TIFF
  • PDF and TIFF, up to 2,000 pages are processed. For free tier subscribers, only the first two pages are processed.
  • The file size must be less than 50 MB and dimensions at least 50 x 50 pixels and at most 10,000 x 10,000 pixels.

Supported languages and locales

See our Language Support page for a complete list of supported languages.

Field extractions

Name Type Description Standardized output
ContactNames Array of objects Contact name
FirstName String First (given) name of contact
LastName String Last (family) name of contact
CompanyNames Array of strings Company name
Departments Array of strings Department or organization of contact
JobTitles Array of strings Listed Job title of contact
Emails Array of strings Contact email address
Websites Array of strings Company website
Addresses Array of strings Address extracted from business card
MobilePhones Array of phone numbers Mobile phone number from business card +1 xxx xxx xxxx
Faxes Array of phone numbers Fax phone number from business card +1 xxx xxx xxxx
WorkPhones Array of phone numbers Work phone number from business card +1 xxx xxx xxxx
OtherPhones Array of phone numbers Other phone number from business card +1 xxx xxx xxxx

Fields extracted

Name Type Description Text
ContactNames array of objects Contact name extracted from business card [{ "FirstName": "John", "LastName": "Doe" }]
FirstName string First (given) name of contact "John"
LastName string Last (family) name of contact "Doe"
CompanyNames array of strings Company name extracted from business card ["Contoso"]
Departments array of strings Department or organization of contact ["R&D"]
JobTitles array of strings Listed Job title of contact ["Software Engineer"]
Emails array of strings Contact email extracted from business card ["johndoe@contoso.com"]
Websites array of strings Website extracted from business card ["https://www.contoso.com"]
Addresses array of strings Address extracted from business card ["123 Main Street, Redmond, Washington 98052"]
MobilePhones array of phone numbers Mobile phone number extracted from business card ["+19876543210"]
Faxes array of phone numbers Fax phone number extracted from business card ["+19876543211"]
WorkPhones array of phone numbers Work phone number extracted from business card ["+19876543231"]
OtherPhones array of phone numbers Other phone number extracted from business card ["+19876543233"]

Supported locales

Prebuilt business cards v2.1 supports the following locales:

  • en-us
  • en-au
  • en-ca
  • en-gb
  • en-in

Migration guide and REST API v3.1

Next steps