title	titleSuffix	description	author	manager	ms.service	ms.topic	ms.date	ms.author
Read model OCR data extraction - Document Intelligence	Azure AI services	Extract print and handwritten text from scanned and digital documents with Document Intelligence's Read OCR model.	laujan	nitinme	azure-ai-document-intelligence	conceptual	10/07/2024	lajanuar

Document Intelligence read model

::: moniker range="doc-intel-4.0.0"

[!INCLUDE preview-version-notice]

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

Note

For extracting text from external images like labels, street signs, and posters, use the Azure AI Image Analysis v4.0 Read feature optimized for general, non-document images with a performance-enhanced synchronous API that makes it easier to embed OCR in your user experience scenarios.

Document Intelligence Read Optical Character Recognition (OCR) model runs at a higher resolution than Azure AI Vision Read and extracts print and handwritten text from PDF documents and scanned images. It also includes support for extracting text from Microsoft Word, Excel, PowerPoint, and HTML documents. It detects paragraphs, text lines, words, locations, and languages. The Read model is the underlying OCR engine for other Document Intelligence prebuilt models like Layout, General Document, Invoice, Receipt, Identity (ID) document, Health insurance card, W2 in addition to custom models.

What is Optical Character Recognition?

Optical Character Recognition (OCR) for documents is optimized for large text-heavy documents in multiple file formats and global languages. It includes features like higher-resolution scanning of document images for better handling of smaller and dense text; paragraph detection; and fillable form management. OCR capabilities also include advanced scenarios like single character boxes and accurate extraction of key fields commonly found in invoices, receipts, and other prebuilt scenarios.

Development options (v4)

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

Feature	Resources	Model ID
Read OCR model	• Document Intelligence Studio • REST API • C# SDK • Python SDK • Java SDK • JavaScript SDK	prebuilt-read

Input requirements (v4)

[!INCLUDE input requirements]

Get started with Read model (v4)

Try extracting text from forms and documents using the Document Intelligence Studio. You need the following assets:

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.

:::image type="content" source="../media/containers/keys-and-endpoint.png" alt-text="Screenshot of keys and endpoint location in the Azure portal.":::

Note

Currently, Document Intelligence Studio doesn't support Microsoft Word, Excel, PowerPoint, and HTML file formats.

Sample document processed with Document Intelligence Studio

:::image type="content" source="../media/studio/form-recognizer-studio-read-v3p2-updated.png" alt-text="Screenshot of Read processing in Document Intelligence Studio.":::

On the Document Intelligence Studio home page, select Read.
You can analyze the sample document or upload your own files.
Select the Run analysis button and, if necessary, configure the Analyze options:

:::image type="content" source="../media/studio/run-analysis-analyze-options.png" alt-text="Screenshot of Run analysis and Analyze options buttons in the Document Intelligence Studio.":::

[!div class="nextstepaction"] Try Document Intelligence Studio.

Supported languages and locales (v4)

See our Language Support—document analysis models page for a complete list of supported languages.

Data extraction (v4)

Note

Microsoft Word and HTML file are supported in v4.0. Compared with PDF and images, below features are not supported:

There are no angle, width/height and unit with each page object.
For each object detected, there is no bounding polygon or bounding region.
Page range (pages) is not supported as a parameter.
No lines object.

Searchable PDFs

The searchable PDF capability enables you to convert an analog PDF, such as scanned-image PDF files, to a PDF with embedded text. The embedded text enables deep text search within the PDF's extracted content by overlaying the detected text entities on top of the image files.

Important

Currently, the searchable PDF capability is only supported by Read OCR model prebuilt-read. When using this feature, please specify the modelId as prebuilt-read, as other model types will return error for this preview version.
Searchable PDF is included with the 2024-07-31-preview prebuilt-read model with no additional cost for generating a searchable PDF output.

Use searchable PDFs

To use searchable PDF, make a POST request using the Analyze operation and specify the output format as pdf:

     POST /documentModels/prebuilt-read:analyze?output=pdf
     {...}
     202

Poll for completion of the Analyze operation. Once the operation is complete, issue a GET request to retrieve the PDF format of the Analyze operation results.

Upon successful completion, the PDF can be retrieved and downloaded as application/pdf. This operation allows direct downloading of the embedded text form of PDF instead of Base64-encoded JSON.

     // Monitor the operation until completion.
     GET /documentModels/prebuilt-read/analyzeResults/{resultId}
     200
     {...}

     // Upon successful completion, retrieve the PDF as application/pdf.
     GET /documentModels/prebuilt-read/analyzeResults/{resultId}/pdf
     200 OK
     Content-Type: application/pdf

Pages parameter

The pages collection is a list of pages within the document. Each page is represented sequentially within the document and includes the orientation angle indicating if the page is rotated and the width and height (dimensions in pixels). The page units in the model output are computed as shown:

File format	Computed page unit	Total pages
Images (JPEG/JPG, PNG, BMP, HEIF)	Each image = 1 page unit	Total images
PDF	Each page in the PDF = 1 page unit	Total pages in the PDF
TIFF	Each image in the TIFF = 1 page unit	Total images in the TIFF
Word (DOCX)	Up to 3,000 characters = 1 page unit, embedded or linked images not supported	Total pages of up to 3,000 characters each
Excel (XLSX)	Each worksheet = 1 page unit, embedded or linked images not supported	Total worksheets
PowerPoint (PPTX)	Each slide = 1 page unit, embedded or linked images not supported	Total slides
HTML	Up to 3,000 characters = 1 page unit, embedded or linked images not supported	Total pages of up to 3,000 characters each

Sample code

    # Analyze pages.
    for page in result.pages:
        print(f"----Analyzing document from page #{page.page_number}----")
        print(f"Page has width: {page.width} and height: {page.height}, measured with unit: {page.unit}")

[!div class="nextstepaction"] View samples on GitHub.

Output

    "pages": [
        {
            "pageNumber": 1,
            "angle": 0,
            "width": 915,
            "height": 1190,
            "unit": "pixel",
            "words": [],
            "lines": [],
            "spans": []
        }
    ]

Use pages for text extraction

For large multi-page PDF documents, use the pages query parameter to indicate specific page numbers or page ranges for text extraction.

Paragraph extraction

The Read OCR model in Document Intelligence extracts all identified blocks of text in the paragraphs collection as a top level object under analyzeResults. Each entry in this collection represents a text block and includes the extracted text ascontent and the bounding polygon coordinates. The span information points to the text fragment within the top-level content property that contains the full text from the document.

    "paragraphs": [
        {
            "spans": [],
            "boundingRegions": [],
            "content": "While healthcare is still in the early stages of its Al journey, we are seeing pharmaceutical and other life sciences organizations making major investments in Al and related technologies.\" TOM LAWRY | National Director for Al, Health and Life Sciences | Microsoft"
        }
    ]

Text, lines, and words extraction

The Read OCR model extracts print and handwritten style text as lines and words. The model outputs bounding polygon coordinates and confidence for the extracted words. The styles collection includes any handwritten style for lines if detected along with the spans pointing to the associated text. This feature applies to supported handwritten languages.

For Microsoft Word, Excel, PowerPoint, and HTML, Document Intelligence Read model v3.1 and later versions extracts all embedded text as is. Texts are extrated as words and paragraphs. Embedded images aren't supported.

Sample code

    # Analyze lines.
    if page.lines:
        for line_idx, line in enumerate(page.lines):
            words = get_words(page, line)
            print(
                f"...Line # {line_idx} has {len(words)} words and text '{line.content}' within bounding polygon '{line.polygon}'"
            )

            # Analyze words.
            for word in words:
                print(f"......Word '{word.content}' has a confidence of {word.confidence}")

[!div class="nextstepaction"] View samples on GitHub.

Output

    "words": [
        {
            "content": "While",
            "polygon": [],
            "confidence": 0.997,
            "span": {}
        },
    ],
    "lines": [
        {
            "content": "While healthcare is still in the early stages of its Al journey, we",
            "polygon": [],
            "spans": [],
        }
    ]

Handwritten style extraction

The response includes classifying whether each text line is of handwriting style or not, along with a confidence score. For more information, see handwritten language support. The following example shows an example JSON snippet.

    "styles": [
    {
        "confidence": 0.95,
        "spans": [
        {
            "offset": 509,
            "length": 24
        }
        "isHandwritten": true
        ]
    }

If you enabled the font/style addon capability, you also get the font/style result as part of the styles object.

Next steps v4.0

Complete a Document Intelligence quickstart:

[!div class="checklist"]

REST API

C# SDK

Python SDK

Java SDK

JavaScript

Explore our REST API:

[!div class="nextstepaction"] Document Intelligence API v4.0

Find more samples on GitHub:

[!div class="nextstepaction"] Read model.

::: moniker-end

::: moniker range="doc-intel-3.1.0" This content applies to: v3.1 (GA) | Latest version: v4.0 (preview) | Previous versions: v3.0 ::: moniker-end

::: moniker range="doc-intel-3.0.0" This content applies to: v3.0 (GA) | Latest versions: v4.0 (preview) v3.1 ::: moniker-end

::: moniker range="<=doc-intel-3.1.0"

Note

For extracting text from external images like labels, street signs, and posters, use the Azure AI Image Analysis v4.0 Read feature optimized for general, non-document images with a performance-enhanced synchronous API that makes it easier to embed OCR in your user experience scenarios.

Document Intelligence Read Optical Character Recognition (OCR) model runs at a higher resolution than Azure AI Vision Read and extracts print and handwritten text from PDF documents and scanned images. It also includes support for extracting text from Microsoft Word, Excel, PowerPoint, and HTML documents. It detects paragraphs, text lines, words, locations, and languages. The Read model is the underlying OCR engine for other Document Intelligence prebuilt models like Layout, General Document, Invoice, Receipt, Identity (ID) document, Health insurance card, W2 in addition to custom models.

What is OCR for documents?

Optical Character Recognition (OCR) for documents is optimized for large text-heavy documents in multiple file formats and global languages. It includes features like higher-resolution scanning of document images for better handling of smaller and dense text; paragraph detection; and fillable form management. OCR capabilities also include advanced scenarios like single character boxes and accurate extraction of key fields commonly found in invoices, receipts, and other prebuilt scenarios.

::: moniker-end

::: moniker range="doc-intel-3.1.0"

Development options

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

Feature	Resources	Model ID
Read OCR model	• Document Intelligence Studio • REST API • C# SDK • Python SDK • Java SDK • JavaScript SDK	prebuilt-read

::: moniker-end

::: moniker range="doc-intel-3.0.0"

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

Feature	Resources	Model ID
Read OCR model	• Document Intelligence Studio • REST API • C# SDK • Python SDK • Java SDK • JavaScript SDK	prebuilt-read

::: moniker-end

::: moniker range="<= doc-intel-3.1.0"

Input requirements

[!INCLUDE input requirements]

Get started with Read model

Try extracting text from forms and documents using the Document Intelligence Studio. You need the following assets:

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.

:::image type="content" source="../media/containers/keys-and-endpoint.png" alt-text="Screenshot of keys and endpoint location in the Azure portal.":::

Note

Currently, Document Intelligence Studio doesn't support Microsoft Word, Excel, PowerPoint, and HTML file formats.

Sample document processed with Document Intelligence Studio

:::image type="content" source="../media/studio/form-recognizer-studio-read-v3p2-updated.png" alt-text="Screenshot of Read processing in Document Intelligence Studio.":::

On the Document Intelligence Studio home page, select Read.
You can analyze the sample document or upload your own files.
Select the Run analysis button and, if necessary, configure the Analyze options:

:::image type="content" source="../media/studio/run-analysis-analyze-options.png" alt-text="Screenshot of Run analysis and Analyze options buttons in the Document Intelligence Studio.":::

[!div class="nextstepaction"] Try Document Intelligence Studio.

Supported languages and locales

See our Language Support—document analysis models page for a complete list of supported languages.

Data extraction

Note

Microsoft Word and HTML file are supported in v3.1 and later versions. Compared with PDF and images, below features are not supported:

There are no angle, width/height and unit with each page object.
For each object detected, there is no bounding polygon or bounding region.
Page range (pages) is not supported as a parameter.
No lines object.

Searchable PDF

The searchable PDF capability enables you to convert an analog PDF, such as scanned-image PDF files, to a PDF with embedded text. The embedded text enables deep text search within the PDF's extracted content by overlaying the detected text entities on top of the image files.

Important

Currently, the searchable PDF capability is only supported by Read OCR model prebuilt-read. When using this feature, please specify the modelId as prebuilt-read, as other model types will return error for this preview version.
Searchable PDF is included with the 2024-07-31-preview prebuilt-read model with no additional cost for generating a searchable PDF output.
- Searchable PDF currently only supports PDF files as input. Support for other file types, such as image files, will be available later.

Use searchable PDF

To use searchable PDF, make a POST request using the Analyze operation and specify the output format as pdf:

    POST /documentModels/prebuilt-read:analyze?output=pdf
    {...}
    202

Poll for completion of the Analyze operation. Once the operation is complete, issue a GET request to retrieve the PDF format of the Analyze operation results.

Upon successful completion, the PDF can be retrieved and downloaded as application/pdf. This operation allows direct downloading of the embedded text form of PDF instead of Base64-encoded JSON.

    // Monitor the operation until completion.
    GET /documentModels/prebuilt-read/analyzeResults/{resultId}
    200
    {...}

    // Upon successful completion, retrieve the PDF as application/pdf.
    GET /documentModels/prebuilt-read/analyzeResults/{resultId}/pdf
    200 OK
    Content-Type: application/pdf

Pages

The pages collection is a list of pages within the document. Each page is represented sequentially within the document and includes the orientation angle indicating if the page is rotated and the width and height (dimensions in pixels). The page units in the model output are computed as shown:

File format	Computed page unit	Total pages
Images (JPEG/JPG, PNG, BMP, HEIF)	Each image = 1 page unit	Total images
PDF	Each page in the PDF = 1 page unit	Total pages in the PDF
TIFF	Each image in the TIFF = 1 page unit	Total images in the TIFF
Word (DOCX)	Up to 3,000 characters = 1 page unit, embedded or linked images not supported	Total pages of up to 3,000 characters each
Excel (XLSX)	Each worksheet = 1 page unit, embedded or linked images not supported	Total worksheets
PowerPoint (PPTX)	Each slide = 1 page unit, embedded or linked images not supported	Total slides
HTML	Up to 3,000 characters = 1 page unit, embedded or linked images not supported	Total pages of up to 3,000 characters each

::: moniker-end

::: moniker range="doc-intel-2.1.0 || doc-intel-3.0.0"

    "pages": [
        {
            "pageNumber": 1,
            "angle": 0,
            "width": 915,
            "height": 1190,
            "unit": "pixel",
            "words": [],
            "lines": [],
            "spans": []
        }
    ]

::: moniker-end

::: moniker range="doc-intel-3.1.0"

Sample code

    # Analyze pages.
    for page in result.pages:
        print(f"----Analyzing document from page #{page.page_number}----")
        print(
            f"Page has width: {page.width} and height: {page.height}, measured with unit: {page.unit}"
        )

[!div class="nextstepaction"] View samples on GitHub.

Output

    "pages": [
        {
            "pageNumber": 1,
            "angle": 0,
            "width": 915,
            "height": 1190,
            "unit": "pixel",
            "words": [],
            "lines": [],
            "spans": []
        }
    ]

::: moniker-end

::: moniker range="<=doc-intel-3.1.0"

Select pages for text extraction

For large multi-page PDF documents, use the pages query parameter to indicate specific page numbers or page ranges for text extraction.

Paragraphs

The Read OCR model in Document Intelligence extracts all identified blocks of text in the paragraphs collection as a top level object under analyzeResults. Each entry in this collection represents a text block and includes the extracted text ascontent and the bounding polygon coordinates. The span information points to the text fragment within the top-level content property that contains the full text from the document.

    "paragraphs": [
        {
            "spans": [],
            "boundingRegions": [],
            "content": "While healthcare is still in the early stages of its Al journey, we are seeing pharmaceutical and other life sciences organizations making major investments in Al and related technologies.\" TOM LAWRY | National Director for Al, Health and Life Sciences | Microsoft"
        }
    ]

Text, lines, and words

The Read OCR model extracts print and handwritten style text as lines and words. The model outputs bounding polygon coordinates and confidence for the extracted words. The styles collection includes any handwritten style for lines if detected along with the spans pointing to the associated text. This feature applies to supported handwritten languages.

For Microsoft Word, Excel, PowerPoint, and HTML, Document Intelligence Read model v3.1 and later versions extracts all embedded text as is. Texts are extrated as words and paragraphs. Embedded images aren't supported.

::: moniker-end

::: moniker range="doc-intel-2.1.0 || doc-intel-3.0.0"

    "words": [
        {
            "content": "While",
            "polygon": [],
            "confidence": 0.997,
            "span": {}
        },
    ],
    "lines": [
        {
            "content": "While healthcare is still in the early stages of its Al journey, we",
            "polygon": [],
            "spans": [],
        }
    ]

::: moniker-end

::: moniker range="doc-intel-3.1.0"

Sample code

    # Analyze lines.
    for line_idx, line in enumerate(page.lines):
        words = line.get_words()
        print(
            f"...Line # {line_idx} has {len(words)} words and text '{line.content}' within bounding polygon '{format_polygon(line.polygon)}'"
        )

        # Analyze words.
        for word in words:
            print(
                f"......Word '{word.content}' has a confidence of {word.confidence}"
            )

[!div class="nextstepaction"] View samples on GitHub.

Output

    "words": [
        {
            "content": "While",
            "polygon": [],
            "confidence": 0.997,
            "span": {}
        },
    ],
    "lines": [
        {
            "content": "While healthcare is still in the early stages of its Al journey, we",
            "polygon": [],
            "spans": [],
        }
    ]

::: moniker-end

::: moniker range="<=doc-intel-3.1.0"

Handwritten style for text lines

The response includes classifying whether each text line is of handwriting style or not, along with a confidence score. For more information, see handwritten language support. The following example shows an example JSON snippet.

    "styles": [
    {
        "confidence": 0.95,
        "spans": [
        {
            "offset": 509,
            "length": 24
        }
        "isHandwritten": true
        ]
    }

If you enabled the font/style addon capability, you also get the font/style result as part of the styles object.

Next steps

Complete a Document Intelligence quickstart:

[!div class="checklist"]

REST API

C# SDK

Python SDK

Java SDK

JavaScript

Explore our REST API:

[!div class="nextstepaction"] Document Intelligence API v4.0

::: moniker-end

::: moniker range="doc-intel-3.1.0"

Find more samples on GitHub:

[!div class="nextstepaction"] Read model.

::: moniker-end

Files

read.md

Latest commit

History

read.md

File metadata and controls

Document Intelligence read model

What is Optical Character Recognition?

Development options (v4)

Input requirements (v4)

Get started with Read model (v4)

Supported languages and locales (v4)

Data extraction (v4)

Searchable PDFs

Use searchable PDFs

Pages parameter

Use pages for text extraction

Paragraph extraction

Text, lines, and words extraction

Handwritten style extraction

Next steps v4.0

What is OCR for documents?

Development options

Input requirements

Get started with Read model

Supported languages and locales

Data extraction

Searchable PDF

Use searchable PDF

Pages

Select pages for text extraction

Paragraphs

Text, lines, and words

Handwritten style for text lines

Next steps