You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/applied-ai-services/form-recognizer/concept-id-document.md
+13-5Lines changed: 13 additions & 5 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -7,7 +7,7 @@ manager: nitinme
7
7
ms.service: applied-ai-services
8
8
ms.subservice: forms-recognizer
9
9
ms.topic: conceptual
10
-
ms.date: 11/10/2022
10
+
ms.date: 11/11/2022
11
11
ms.author: lajanuar
12
12
recommendations: false
13
13
ms.custom: references.regions
@@ -24,13 +24,21 @@ ms.custom: references.regions
24
24
[!INCLUDE [applies to v2.1](includes/applies-to-v2-1.md)]
25
25
::: moniker-end
26
26
27
-
Azure Form Recognizer Identity document (ID) model combines Optical Character Recognition (OCR) with deep learning models to analyze and extract key information from identity documents: US Drivers Licenses (all 50 states and District of Columbia), international passport biographical pages, US state IDs, social security cards, and permanent resident cards and more. The API analyzes identity documents, extracts key information, and returns a structured JSON data representation.
27
+
::: moniker range="form-recog-3.0.0"
28
28
29
-
## Identity document processing
29
+
Azure Form Recognizer Identity document (ID) model combines Optical Character Recognition (OCR) with deep learning models to analyze and extract key information from identity documents such as US Drivers Licenses (all 50 states and District of Columbia), international passport biographical pages, US state IDs, social security cards, and permanent resident cards and more. The API analyzes identity documents, extracts key information, and returns a structured JSON data representation.
30
+
31
+
::: moniker-end
32
+
33
+
::: moniker range="form-recog-2.1.0"
34
+
35
+
Azure Form Recognizer can analyze and extract information from government-issued identification documents (IDs) using its prebuilt IDs model. It combines our powerful [Optical Character Recognition (OCR)](../computer-vision/overview-ocr.md) capabilities with ID recognition capabilities to extract key information from Worldwide Passports and U.S. Driver's Licenses (all 50 states and D.C.). The IDs API extracts key information from these identity documents, such as first name, last name, date of birth, document number, and more. This API is available in the Form Recognizer v2.1 as a cloud service.
30
36
31
-
Identity document processing involves extracting data from identity documents either manually or by using OCR based techniques. Examples of identity documents include passports, driver licenses, resident cards, and national identity cards like the US social security card.
37
+
::: moniker-end
38
+
39
+
## Identity document processing
32
40
33
-
ID document processing an important step in any business process that requires some proof of identity. Examples include customer verification in banks and other financial institutions, mortgage applications, medical visits, claim processing, hospitality industry, and more. Individuals provide some proof of their identity via driver licenses, passports, and other similar documents so that the business can efficiently verify them before providing services and benefits.
41
+
Identity document processing involves extracting data from identity documents either manually or by using OCR-based technology. ID document is processing an important step in any business process that requires some proof of identity. Examples include customer verification in banks and other financial institutions, mortgage applications, medical visits, claim processing, hospitality industry, and more. Individuals provide some proof of their identity via driver licenses, passports, and other similar documents so that the business can efficiently verify them before providing services and benefits.
Copy file name to clipboardExpand all lines: articles/applied-ai-services/form-recognizer/concept-layout.md
+56-52Lines changed: 56 additions & 52 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -14,8 +14,6 @@ recommendations: false
14
14
15
15
# Azure Form Recognizer layout model
16
16
17
-
The Form Recognizer Layout is an advanced machine-learning based document layout analysis model available in the Form Recognizer cloud API. In the version v2.1, the document layout model extracted text lines, words, tables, and selection marks.
18
-
19
17
::: moniker range="form-recog-3.0.0"
20
18
[!INCLUDE [applies to v3.0](includes/applies-to-v3-0.md)]
21
19
::: moniker-end
@@ -24,9 +22,14 @@ The Form Recognizer Layout is an advanced machine-learning based document layout
24
22
[!INCLUDE [applies to v2.1](includes/applies-to-v2-1.md)]
25
23
::: moniker-end
26
24
25
+
Form Recognizer layout model is an advanced machine-learning based document analysis API available in the Form Recognizer cloud. It enables you to take documents in a variety of formats and return structured data representations of the documents. It combines an enhanced version of our powerful [Optical Character Recognition (OCR)](../../cognitive-services/Bing-Autosuggest/computer-vision/overview-ocr.md) capabilities with deep learning models to extract text, tables, selection marks, and document structure.
26
+
27
27
## Document layout analysis
28
28
29
-
Document structure layout analysis is the process of analyzing a document to extract regions of interest and their inter-relationships. The goal is to extract text and structural elements from the page for building better semantic understanding models. For all extracted text, there are two types of roles that text plays in a document layout. Text, tables, and selection marks are examples of geometric roles. Titles, headings, and footers are examples of logical roles. For example, a reading system requires differentiating text regions from non-textual ones along with their reading order.
29
+
Document structure layout analysis is the process of analyzing a document to extract regions of interest and their inter-relationships. The goal is to extract text and structural elements from the page to build better semantic understanding models. There are two types of roles that text plays in a document layout:
30
+
31
+
***Geometric roles**: Text, tables, and selection marks are examples of geometric roles.
32
+
***Logical roles**: Titles, headings, and footers are examples of logical roles.
30
33
31
34
The following illustration shows the typical components in an image of a sample page.
32
35
@@ -38,64 +41,37 @@ The following illustration shows the typical components in an image of a sample
38
41
39
42
:::image type="content" source="media/studio/form-recognizer-studio-layout-newspaper.png" alt-text="Screenshot of sample newspaper page processed using Form Recognizer studio":::
40
43
44
+
## Development options
45
+
46
+
The following tools are supported by Form Recognizer v3.0:
:::image type="content" source="media/layout-tool-example.jpg" alt-text="Screenshot of a document processed with the layout model.":::
48
-
::: moniker-end
49
59
50
-
## Supported document types
60
+
::: moniker-end
51
61
52
-
|**Model**|**Images**|**PDF**|**TIFF**|
53
-
| --- | --- | --- | --- |
54
-
| Layout | ✓ | ✓ | ✓ |
62
+
## Input requirements
55
63
56
64
::: moniker range="form-recog-3.0.0"
57
65
58
-
### Data extraction
59
-
60
-
**Starting with v3.0 GA**, it extracts paragraphs and more structure information like titles, section headings, page header, page footer, page number, and footnote from the document page. These structural elements are examples of logical roles described in the previous section. This capability is supported for PDF documents and images (JPG, PNG, BMP, TIFF).
The paragraph roles are best used with unstructured documents. Paragraph roles help analyze the structure of the extracted content for better semantic search and analysis.
68
-
69
-
* title
70
-
* sectionHeading
71
-
* footnote
72
-
* pageHeader
73
-
* pageFooter
74
-
* pageNumber
75
-
76
-
## Development options
77
-
78
-
The following tools are supported by Form Recognizer v3.0:
**Starting with v3.0 GA**, it extracts paragraphs and more structure information like titles, section headings, page header, page footer, page number, and footnote from the document page. These structural elements are examples of logical roles described in the previous section. This capability is supported for PDF documents and images (JPG, PNG, BMP, TIFF).
The paragraph roles are best used with unstructured documents. Paragraph roles help analyze the structure of the extracted content for better semantic search and analysis.
164
+
165
+
* title
166
+
* sectionHeading
167
+
* footnote
168
+
* pageHeader
169
+
* pageFooter
170
+
* pageNumber
171
171
172
172
::: moniker-end
173
173
174
174
::: moniker range="form-recog-2.1.0"
175
175
176
-
* Supported file formats: JPEG, PNG, PDF, and TIFF
177
-
* For PDF and TIFF, up to 2000 pages are processed. For free tier subscribers, only the first two pages are processed.
178
-
* 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.
176
+
### Data extraction
179
177
180
-
::: moniker-end
178
+
|**Model**|**Text**|**Tables**| Selection marks|
179
+
| --- | --- | --- | --- |
180
+
| Layout | ✓ | ✓| ✓ |
181
181
182
-
## Supported languages and locales
182
+
The following tools are supported by Form Recognizer v2.1:
183
183
184
-
*See*[Language Support](language-support.md) for a complete list of supported handwritten and printed languages.
0 commit comments