Edit

Share via

Document Intelligence receipt model

  • Article

Important

  • Document Intelligence public preview releases provide early access to features that are in active development. Features, approaches, and processes may change, prior to General Availability (GA), based on user feedback.
  • The public preview version of Document Intelligence client libraries default to REST API version 2024-07-31-preview.
  • Public preview version 2024-07-31-preview is currently only available in the following Azure regions. Note that the custom generative (document field extraction) model in AI Foundry portal is only available in North Central US region:
    • East US
    • West US2
    • West Europe
    • North Central US

This content applies to: checkmark v4.0 (preview) | Previous versions: blue-checkmark v3.1 (GA) blue-checkmark v3.0 (GA) blue-checkmark v2.1 (GA)

This content applies to: checkmark v3.1 (GA) | Latest version: purple-checkmark v4.0 (preview) | Previous versions: blue-checkmark v3.0 blue-checkmark v2.1

This content applies to: checkmark v3.0 (GA) | Latest versions: purple-checkmark v4.0 (preview) purple-checkmark v3.1 | Previous version: blue-checkmark v2.1

This content applies to: checkmark v2.1 | Latest version: blue-checkmark v4.0 (preview)

The Document Intelligence receipt model combines powerful Optical Character Recognition (OCR) capabilities with deep learning models to analyze and extract key information from sales receipts. Receipts can be of various formats and quality including printed and handwritten receipts. The API extracts key information such as merchant name, merchant phone number, transaction date, tax, and transaction total and returns structured JSON data.

Supported receipt types:

  • Thermal
  • Credit Card
  • Gas
  • Parking
  • Hotel
  • Transportation
  • Communication
  • Entertainment
  • Flight
  • Training
  • Pharmacy/Medical

Receipt data extraction

Receipt digitization encompasses the transformation of various types of receipts, including scanned, photographed, and printed copies, into a digital format for streamlined downstream processing. Examples include expense management, consumer behavior analysis, tax automation, etc. Using Document Intelligence with OCR (Optical Character Recognition) technology can extract and interpret data from these diverse receipt formats. Document Intelligence processing simplifies the conversion process but also significantly reduces the time and effort required, thus facilitating efficient data management, and retrieval.

Sample receipt processed with Document Intelligence Studio:

Screenshot of a sample receipt processed in the Document Intelligence Studio.

Sample receipt processed with Document Intelligence Sample Labeling tool:

Screenshot of a sample receipt processed with the Form Sample Labeling tool.

Development options

Document Intelligence v4.0 (2024-07-31-preview) supports the following tools, applications, and libraries:

Feature Resources Model ID
Receipt model • Document Intelligence Studio
• REST API
• C# SDK
• Python SDK
• Java SDK
• JavaScript SDK		 prebuilt-receipt

Document Intelligence v3.1 supports the following tools, applications, and libraries:

Feature Resources Model ID
Receipt model • Document Intelligence Studio
• REST API
• C# SDK
• Python SDK
• Java SDK
• JavaScript SDK		 prebuilt-receipt

Document Intelligence v3.0 supports the following tools, applications, and libraries:

Feature Resources Model ID
Receipt model • Document Intelligence Studio
• REST API
• C# SDK
• Python SDK
• Java SDK
• JavaScript SDK		 prebuilt-receipt

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

Feature Resources
Receipt model • Document Intelligence labeling tool
• REST API
• Client-library SDK
• Document Intelligence Docker container

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.

  • Supported file formats: JPEG, PNG, PDF, and TIFF.
  • Supported page allowance for PDF and TIFF: Document Intelligence can process up to 2,000 pages for standard tier subscribers or only the first two pages for free-tier subscribers.
  • Supported file size: less than 50 MB; minimum pixels 50 x 50 px; maximum pixels 10,000 x 10,000 px.

Receipt model data extraction

See how Document Intelligence extracts data, including time and date of transactions, merchant information, and amount totals from receipts. You need the following resources:

  • An Azure subscription—you can create one for free.

  • A Document Intelligence instance in the Azure portal. You can use the free pricing tier (F0) to try the service. After your resource deploys, select Go to resource to get your key and endpoint.

Screenshot of keys and endpoint location in the Azure portal.

Note

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

  1. On the Document Intelligence Studio home page, select Receipts.

  2. You can analyze the sample receipt 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.

    Try 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 process.

  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 layout 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.

Supported languages and locales

For a complete list of supported languages, see our prebuilt models language support page.

Field extraction

Name Type Description Standardized output
ReceiptType String Type of sales receipt Itemized
MerchantName String Name of the merchant issuing the receipt
MerchantPhoneNumber phoneNumber Listed phone number of merchant +1 xxx xxx xxxx
MerchantAddress String Listed address of merchant
TransactionDate Date Date the receipt was issued yyyy-mm-dd
TransactionTime Time Time the receipt was issued hh-mm-ss (24-hour)
Total Number (USD) Full transaction total of receipt Two-decimal float
Subtotal Number (USD) Subtotal of receipt, often before taxes are applied Two-decimal float
Tax Number (USD) Total tax on receipt (often sales tax, or equivalent). Renamed to "TotalTax" in 2022-06-30 version. Two-decimal float
Tip Number (USD) Tip included by buyer Two-decimal float
Items Array of objects Extracted line items, with name, quantity, unit price, and total price extracted
Name String Item description. Renamed to "Description" in 2022-06-30 version.
Quantity Number Quantity of each item Two-decimal float
Price Number Individual price of each item unit Two-decimal float
TotalPrice Number Total price of line item Two-decimal float

For supported document extraction fields, refer to the receipt model schema page in our GitHub sample repository.

Migration guide and REST API v3.1

Next steps