Merge pull request #188364 from sanjeev3/patch-1

Sanjeev> Form Recognizer Preview 2 Release Updates

Author: laurabren

articles/applied-ai-services/form-recognizer/concept-accuracy-confidence.md

@@ -70,4 +70,4 @@ The accuracy of your model is affected by variances in the visual structure of y
 ## Next step
 
 > [!div class="nextstepaction"]
-> [Learn to create custom models ](quickstarts/try-v3-form-recognizer-studio.md#getting-started)
+> [Learn to create custom models ](quickstarts/try-v3-form-recognizer-studio.md#custom-models)

articles/applied-ai-services/form-recognizer/concept-custom.md

@@ -123,7 +123,7 @@ The [Sample Labeling tool](https://fott-2-1.azurewebsites.net/) doesn't support
 
 ## Supported languages and locales
 
- The Form Recognizer preview version introduces more language support for custom models. For a list of supported handwritten and printed text, see [Language support](language-support.md#layout-and-custom-model).
+ The Form Recognizer preview version introduces more language support for custom models. For a list of supported handwritten and printed text, see [Language support](language-support.md).
 
 ## Form Recognizer v3.0 (preview)
 

articles/applied-ai-services/form-recognizer/concept-form-recognizer-studio.md

@@ -27,13 +27,15 @@ The following image shows the Invoice prebuilt model feature at work.
 
 The following Form Recognizer service features are available in the Studio.
 
-* **Layout**: Try out Form Recognizer's Layout feature to extract text, tables, selection marks, and structure information from documents—PDF, TIFF—and images—JPG, PNG, BMP. Start with the [Studio Layout quickstart](quickstarts/try-v3-form-recognizer-studio.md#layout). Explore with sample documents and your documents. Use the interactive visualization and JSON output to understand how the feature works. See the [Layout overview](concept-layout.md) to learn more and get started with the [Python SDK quickstart for Layout](quickstarts/try-v3-python-sdk.md#layout-model).
+* **Read**: Try out Form Recognizer's Read feature to extract text lines, words, detected languages, and handwritten style if detected. Start with the [Studio Read feature](https://formrecognizer.appliedai.azure.com/studio/read). Explore with sample documents and your documents. Use the interactive visualization and JSON output to understand how the feature works. See the [Read overview](concept-read.md) to learn more and get started with the [Python SDK quickstart for Layout](quickstarts/try-v3-python-sdk.md).
 
-* **Prebuilt models**: Form Recognizer's pre-built models enable you to add intelligent document processing to your apps and flows without having to train and build your own models. Start with the [Studio Prebuilts quickstart](quickstarts/try-v3-form-recognizer-studio.md#prebuilt-models). Explore with sample documents and your documents. Use the interactive visualization, extracted fields list, and JSON output to understand how the feature works. See the [Models overview](concept-model-overview.md) to learn more and get started with the [Python SDK quickstart for Prebuilt Invoice](quickstarts/try-v3-python-sdk.md#prebuilt-model).
+* **Layout**: Try out Form Recognizer's Layout feature to extract text, tables, selection marks, and structure information. Start with the [Studio Layout feature](https://formrecognizer.appliedai.azure.com/studio/layout). Explore with sample documents and your documents. Use the interactive visualization and JSON output to understand how the feature works. See the [Layout overview](concept-layout.md) to learn more and get started with the [Python SDK quickstart for Layout](quickstarts/try-v3-python-sdk.md#layout-model).
 
-* **Custom models**: Form Recognizer's custom models enable you to extract fields and values from models trained with your data, tailored to your forms and documents. Create standalone custom models or combine two or more custom models to create a composed model to extract data from multiple form types. Start with the [Studio Custom models quickstart](quickstarts/try-v3-form-recognizer-studio.md#custom-projects).  Use the online wizard, labeling interface, training step, and visualizations to understand how the feature works. Test the custom model with your sample documents and iterate to improve the model. See the [Custom models overview](concept-custom.md) to learn more and use the [Form Recognizer v3.0 preview migration guide](v3-migration-guide.md) to start integrating the new models with your applications.
+* **General Documents**: Try out Form Recognizer's General Documents feature to extract key-value pairs and entities. Start with the [Studio General Documents feature](https://formrecognizer.appliedai.azure.com/studio/document). Explore with sample documents and your documents. Use the interactive visualization and JSON output to understand how the feature works. See the [General Documents overview](concept-general-document.md) to learn more and get started with the [Python SDK quickstart for Layout](quickstarts/try-v3-python-sdk.md#general-document-model).
 
-* **Custom models: Labeling features**: Form Recognizer Custom model creation requires identifying the fields to be extracted and labeling  those fields before training the custom models. Labeling text, selection marks, tabular data, and other content types are typically assisted with a user interface to ease the training workflow. For example, use the [Label as tables](quickstarts/try-v3-form-recognizer-studio.md#labeling-as-tables) and [Labeling for signature detection](quickstarts/try-v3-form-recognizer-studio.md#labeling-for-signature-detection) quickstarts to understand the labeling experience in Form Recognizer Studio.
+* **Prebuilt models**: Form Recognizer's pre-built models enable you to add intelligent document processing to your apps and flows without having to train and build your own models. As an example, start with the [Studio Invoice feature](https://formrecognizer.appliedai.azure.com/studio/prebuilt?formType=invoice). Explore with sample documents and your documents. Use the interactive visualization, extracted fields list, and JSON output to understand how the feature works. See the [Models overview](concept-model-overview.md) to learn more and get started with the [Python SDK quickstart for Prebuilt Invoice](quickstarts/try-v3-python-sdk.md#prebuilt-model).
+
+* **Custom models**: Form Recognizer's custom models enable you to extract fields and values from models trained with your data, tailored to your forms and documents. Create standalone custom models or combine two or more custom models to create a composed model to extract data from multiple form types. Start with the [Studio Custom models feature](https://formrecognizer.appliedai.azure.com/studio/custommodel/projects).  Use the online wizard, labeling interface, training step, and visualizations to understand how the feature works. Test the custom model with your sample documents and iterate to improve the model. See the [Custom models overview](concept-custom.md) to learn more and use the [Form Recognizer v3.0 preview migration guide](v3-migration-guide.md) to start integrating the new models with your applications.
 
 ## Next steps
 

articles/applied-ai-services/form-recognizer/concept-layout.md

@@ -15,7 +15,7 @@ ms.custom: ignite-fall-2021
 
 # Form Recognizer layout model
 
-Azure the Form Recognizer Layout API extracts text, tables, selection marks, and structure information from documents (PDF, TIFF) and images (JPG, PNG, BMP).  The layout model combines an enhanced version of our powerful [Optical Character Recognition (OCR)](../../cognitive-services/computer-vision/overview-ocr.md) capabilities with deep learning models to extract text, tables, selection marks, and document structure.
+The Form Recognizer Layout API extracts text, tables, selection marks, and structure information from documents (PDF, TIFF) and images (JPG, PNG, BMP).
 
 ***Sample form processed with [Form Recognizer Sample Labeling tool](https://fott-2-1.azurewebsites.net/)  layout feature***
 
@@ -58,7 +58,7 @@ See how data, including tables, check boxes, and text, is extracted from forms a
 
 ***Sample form processed with [Form Recognizer Studio](https://formrecognizer.appliedai.azure.com/studio/layout)***
 
-:::image type="content" source="media/studio/sample-layout.png" alt-text="Screenshot: document processing in Form Recognizer Studio.":::
+:::image type="content" source="media/studio/form-recognizer-studio-layout-v3p2.png" alt-text="Screenshot: Layout processing in Form Recognizer Studio.":::
 
 1. On the Form Recognizer Studio home page, select **Layout**
 
@@ -93,19 +93,13 @@ You'll need a form document. You can use our [sample form document](https://raw.
 * For PDF and TIFF, up to 2000 pages can be processed (with a free tier subscription, only the first two pages are processed).
 * The file size must be less than 50 MB.
 * Image dimensions must be between 50 x 50 pixels and 10000 x 10000 pixels.
-* PDF dimensions are up to 17 x 17 inches, corresponding to Legal or A3 paper size, or smaller.
-* The total size of the training data is 500 pages or less.
-* If your PDFs are password-locked, you must remove the lock before submission.
-* For unsupervised learning (without labeled data):
-  * Data must contain keys and values.
-  * Keys must appear above or to the left of the values; they can't appear below or to the right.
 
 > [!NOTE]
 > The [Sample Labeling tool](https://fott-2-1.azurewebsites.net/) does not support the BMP file format. This is a limitation of the tool not the Form Recognizer Service.
 
 ## Supported languages and locales
 
- Form Recognizer preview version introduces additional language support for the layout model. *See* our [Language Support](language-support.md#layout-and-custom-model) for a complete list of supported handwritten and printed text.
+ Form Recognizer preview version introduces additional language support for the layout model. *See* our [Language Support](language-support.md) for a complete list of supported handwritten and printed languages.
 
 ## Features
 
@@ -129,21 +123,17 @@ Layout API extracts text from documents and images with multiple text angles and
 
 ### Natural reading order for text lines (Latin only)
 
-You can specify the order in which the text lines are output with the `readingOrder` query parameter. Use `natural` for a more human-friendly reading order output as shown in the following example. This feature is only supported for Latin languages.
+In Form Recognizer v2.1, you can specify the order in which the text lines are output with the `readingOrder` query parameter. Use `natural` for a more human-friendly reading order output as shown in the following example. This feature is only supported for Latin languages.
 
-:::image type="content" source="./media/layout-reading-order-example.png" alt-text="Layout Reading order example" lightbox="../../cognitive-services/Computer-vision/Images/ocr-reading-order-example.png":::
+In Form Recognizer v3.0, the natural reading order output is used by the service in all cases. Therefore, there is no `readingOrder` parameter provided in this version.
 
 ### Handwritten classification for text lines (Latin only)
 
-The response includes classifying whether each text line is of handwriting style or not, along with a confidence score. This feature is only supported for Latin languages. The following example shows the handwritten classification for the text in the image.
-
-:::image type="content" source="./media/layout-handwriting-classification.png" alt-text="handwriting classification example":::
+The response includes classifying whether each text line is of handwriting style or not, along with a confidence score. This feature is only supported for Latin languages. 
 
 ### Select page numbers or ranges for text extraction
 
-For large multi-page documents, use the `pages` query parameter to indicate specific page numbers or page ranges for text extraction. The following example shows a document with 10 pages, with text extracted for both cases - all pages (1-10) and selected pages (3-6).
-
-:::image type="content" source="./media/layout-select-pages-for-text.png" alt-text="Layout selected pages output":::
+For large multi-page documents, use the `pages` query parameter to indicate specific page numbers or page ranges for text extraction. 
 
 ## Form Recognizer preview v3.0
 

articles/applied-ai-services/form-recognizer/concept-model-overview.md

@@ -16,12 +16,13 @@ ms.custom: ignite-fall-2021
 
 # Form Recognizer models
 
- Azure Form Recognizer prebuilt models enable you to add intelligent document processing to your apps and flows without having to train and build your own models. Prebuilt models use optical character recognition (OCR) combined with deep learning models to identify and extract predefined text and data fields common to specific form and document types. Form Recognizer extracts analyzes form and document data then  returns an organized, structured JSON response. Form Recognizer v2.1 supports invoice, receipt, ID document, and business card models.
+Azure Form Recognizer prebuilt models enable you to add intelligent document processing to your apps and flows without having to train and build your own models. Prebuilt models use optical character recognition (OCR) combined with deep learning models to identify and extract predefined text and data fields common to specific form and document types. Form Recognizer extracts analyzes form and document data then  returns an organized, structured JSON response. Form Recognizer v2.1 supports invoice, receipt, ID document, and business card models.
 
 ## Model overview
 
 | **Model**   | **Description**   |
 | --- | --- |
+| 🆕[Read (preview)](#read-preview) | Extract text lines, words, their locations, detected languages, and handwritten style if detected.  |
 | 🆕[General document (preview)](#general-document-preview) | Extract text, tables, structure, key-value pairs, and named entities.  |
 | [Layout](#layout)  | Extracts text and layout information from documents.  |
 | [Invoice](#invoice)  | Extract key information from English and Spanish invoices.  |
@@ -30,6 +31,19 @@ ms.custom: ignite-fall-2021
 | [Business card](#business-card)  | Extract key information from English business cards.  |
 | [Custom](#custom) |  Extract data from forms and documents specific to your business. Custom models are trained for your distinct data and use cases. |
 
+### Read (preview)
+
+:::image type="content" source="media/studio/read-card.png" alt-text="Screenshot: Studio read icon.":::
+
+The Read API analyzes and extracts ext lines, words, their locations, detected languages, and handwritten style if detected.
+
+***Sample document processed using the [Form Recognizer Studio](https://formrecognizer.appliedai.azure.com/studio/read)***:
+
+:::image type="content" source="media/studio/form-recognizer-studio-read-v3p2.png" alt-text="Screenshot: Screenshot of sample document processed using Form Recognizer studio Read":::
+
+> [!div class="nextstepaction"]
+> [Learn more: read model](concept-read.md)
+
 ### General document (preview)
 
 :::image type="content" source="media/studio/general-document.png" alt-text="Screenshot: Studio general document icon.":::
@@ -128,15 +142,17 @@ The custom model analyzes and extracts data from forms and documents specific to
 ## Data extraction
 
  | **Model**   | **Text extraction** |**Key-Value pairs** |**Fields**|**Selection Marks**   | **Tables**   |**Entities** |
-  | --- |: ---: |:---:|: ---: |: ---: |:---: |:---: |
-  |🆕General document  | ✓  |  ✓ || ✓  | ✓  | ✓  |
+  | --- | :---: |:---:| :---: | :---: |:---: |:---: |
+  |🆕Read (preview) | ✓ |   ||   |   |   |
+  |🆕General document (preview)  | ✓  |  ✓ || ✓  | ✓  | ✓  |
   | Layout  | ✓  |   || ✓  | ✓  |   |
   | Invoice  | ✓ | ✓  |✓| ✓  | ✓ ||
   |Receipt  | ✓  |   ✓ |✓|   |  ||
   | ID document | ✓  |   ✓  |✓|   |   ||
   | Business card    | ✓  |   ✓ | ✓|  |   ||
   | Custom             |✓  |  ✓ || ✓  | ✓  | ✓  |
 
+
 ## Input requirements
 
 * For best results, provide one clear photo or high-quality scan per document.
@@ -158,6 +174,7 @@ The custom model analyzes and extracts data from forms and documents specific to
 
   Form Recognizer v3.0 (preview) introduces several new features and capabilities:
 
+* [**Read (preview)**](concept-read.md) model is a new API that extracts text lines, words, their locations, detected languages, and handwrting style if detected.
 * [**General document (preview)**](concept-general-document.md) model is a new API that uses a pre-trained model to extract text, tables, structure, key-value pairs, and named entities from forms and documents.
 * [**Receipt (preview)**](concept-receipt.md) model supports single-page hotel receipt processing.
 * [**ID document (preview)**](concept-id-document.md) model supports endorsements, restrictions, and vehicle classification extraction from US driver's licenses.