Azure OCR (OCR Engine) - Revision history

Dgreenwood at 19:53, 18 March 2026

2026-03-18T19:53:31Z

← Older revision		Revision as of 14:53, 18 March 2026
Line 1:		Line 1:
			{\|class="important-box"
			\|
			‼
			\|
			The '''Azure OCR''' engine only exposes the Read engine up to version 3.2. Furthermore, Microsoft will retire Read v3.2 and below '''September 25, 2028'''.

			The '''[[Azure DI OCR]]''' engine exposes the most recent version of the Read engine.
			* New implementations should use the Azure DI OCR engine instead.
			* Existing implementations must migrate to the Azure DI OCR engine by September 25, 2028.
			\|}

	{{AutoVersion}}		{{AutoVersion}}

Dgreenwood: /* Segment Reprocessing incompatibility */

2025-04-03T19:24:41Z

Segment Reprocessing incompatibility

← Older revision		Revision as of 14:24, 3 April 2025
Line 151:		Line 151:
	[[File:2024 Azure-OCR 02 03 02.png]]		[[File:2024 Azure-OCR 02 03 02.png]]

	== Segment Reprocessing incompatibility ==		== Image Segmentation and Segment Reprocessing incompatibility ==

	Azure OCR is NOT compatible with ~~the~~ Segment Reprocessing ~~feature~~. The Read API will return an error if you attempt to configure ~~this property~~ in an OCR Profile. The image snippets Grooper uses to ~~reprocess~~ the segments fall under Azure's minimum image dimensions.		Azure OCR is NOT compatible with Grooper's "Image Segmentation" and "Segment Reprocessing" Synthesis features. The Read API will return an error if you attempt to configure these properties in an OCR Profile. The image snippets Grooper uses to process the segments fall under Azure's minimum image dimensions.

			OUR BEST PRACTICE ADVICE: Set the "Synthesis" property to Disabled when using Azure OCR in an OCR Profile.

Dgreenwood: /* Known Concerns */

2025-04-03T19:16:59Z

Known Concerns

← Older revision		Revision as of 14:16, 3 April 2025
Line 151:		Line 151:
	[[File:2024 Azure-OCR 02 03 02.png]]		[[File:2024 Azure-OCR 02 03 02.png]]

	== ~~Known Concerns~~ ==		== Segment Reprocessing incompatibility ==

	Azure OCR is NOT compatible with the Segment Reprocessing feature. The Read API will return an error if you attempt to configure this property in an OCR Profile. The image snippets Grooper uses to reprocess the segments fall under Azure's minimum image dimensions.		Azure OCR is NOT compatible with the Segment Reprocessing feature. The Read API will return an error if you attempt to configure this property in an OCR Profile. The image snippets Grooper uses to reprocess the segments fall under Azure's minimum image dimensions.

Dgreenwood at 19:15, 3 April 2025

2025-04-03T19:15:06Z

← Older revision		Revision as of 14:15, 3 April 2025
Line 150:		Line 150:

	[[File:2024 Azure-OCR 02 03 02.png]]		[[File:2024 Azure-OCR 02 03 02.png]]

			== Known Concerns ==

			Azure OCR is NOT compatible with the Segment Reprocessing feature. The Read API will return an error if you attempt to configure this property in an OCR Profile. The image snippets Grooper uses to reprocess the segments fall under Azure's minimum image dimensions.

Dgreenwood: /* About */

2025-01-10T22:59:12Z

About

← Older revision		Revision as of 17:59, 10 January 2025
Line 14:		Line 14:
	== About ==		== About ==

	'''''Azure OCR''''' is different from traditional '''''[[OCR Engine]]s'''''. It is a CNN (Convolutional Neural Network) based ~~'''''~~OCR ~~Engine''''' meaning that it is AI based~~. ~~Due~~ to the ~~way this neural network has been trained, '''''Azure~~ OCR~~''''' is less dependent on '''''[[Image Processing]]'''''~~.		'''''Azure OCR''''' is different from traditional '''''[[OCR Engine]]s'''''. It uses Microsoft Azure's Read OCR engine which is a CNN (Convolutional Neural Network) based OCR engine. This uses a deep learning neural network to recognize characters from full images (as opposed to the segmentation-based matrix matching methods traditional OCR engines use).

	Unlike traditional [[OCR]], '~~''''~~Azure ~~OCR'''''~~ has a far higher accuracy when recognizing ~~handwritten~~ text ~~on documents~~. ~~However~~, ~~'''''Azure~~ OCR~~''''' alone does not give 100% accurate position data~~ of ~~characters~~, ~~it only gives us an approximation~~. This ~~can cause problems~~ for ~~extractors that are reliant on character/text positions such as~~ '''~~''[[Labeled Value]]''''', '~~'''~~'[[Labeled OMR]]''''', or '''''[[Tabular Layout]]'''''.~~ '''''Azure OCR''''' ~~also does not always capture smaller numeric values such as 1s and 0s. This can make collecting some data problematic~~.		Unlike traditional [[OCR]], Microsoft's Azure Read engine has a far higher accuracy over all when recognizing text from an image. It is capable of recognizing hand printed characters, which many traditional OCR engines cannot do at all. It is also as good or better at a wide variety of machine print fonts as traditional OCR engines. This includes specialized fonts like MICR. Furthermore, due to the way this neural network has been trained, the Azure Read engine is less depending on image pre-processing than traditional OCR engines. This eliminates the need for complicated '''IP Profiles''' when using '''''Azure OCR''''' in Grooper.

	~~To compensate~~, a traditional ~~'''~~OCR ~~Engine''' (~~Transym~~) runs at~~ the ~~same time when using '''''~~Azure ~~OCR''''' because traditional OCR is highly effective at obtaining~~ position ~~data and~~ can ~~capture smaller values. A traditional '''OCR Engine''' is more dependent~~ on '''''~~Image Processing~~'''''~~. When choosing~~ '''''~~Azure OCR~~''''', ~~a default set of~~ '''''~~Image Processing~~''''' ~~steps are applied to~~ the ~~document to improve traditional OCR accuracy~~.		However, the Azure Read engine does have some drawbacks compared to traditional OCR. Unlike traditional OCR engines, like Transym, the Azure Read engine does not return the pixel-accurate position of characters. It only gives us an approximation. This can cause problems for extractors that are reliant on character/text positions such as '''''[[Labeled Value]]''''', '''''[[Labeled OMR]]''''', or '''''[[Tabular Layout]]'''''. The Azure Read engine also does not always capture data correctly from "data dense" documents littered with text on tables. This is particularly the case for tabular data with cells containing single characters, (such "0" or "1" or "A"). This can make collecting certain data structures problematic.

	Grooper ~~attempts to return the most accurate results from both~~ the '''''Azure OCR''''' ~~and the~~ traditional '''OCR ~~Engine''~~'.		Grooper's implementation of the Azure Read engine compensates for these shortcomings (and more). Using our '''''Azure OCR''''' offering, a traditional OCR engine (Transym) runs in parallel with Azure's Read engine. Results from Transym supplement Azure's results with more accurate character positions and values in areas we have found Azure to be deficient. This gives us the best in both worlds in terms of the Azure Read engine's strengths and traditional OCR engines' strengths.

	Supported image types: JPEG, PNG, BMP, PDF, and TIFF		Supported image types: JPEG, PNG, BMP, PDF, and TIFF
Line 35:		Line 35:

	Azure OCR has many advantages over traditional OCR engines (such as Transym).		Azure OCR has many advantages over traditional OCR engines (such as Transym).
	* Azure OCR is less dependent on image processing than traditional OCR engines. It can handle poor quality images and even photos taken with a digital camera or phone camera without the aid of an '''IP Profile'''.		* Azure OCR is less dependent on image processing than traditional OCR engines.
			* It can handle poor quality images and even photos taken with a digital camera or phone camera without the aid of an '''IP Profile'''.
	* Azure OCR has exceptionally good handwritten text recognition. Traditional OCR engines have poor handwriting recognition or none at all.		* Azure OCR has exceptionally good handwritten text recognition. Traditional OCR engines have poor handwriting recognition or none at all.
	* Azure OCR's machine print recognition is generally as good or better than traditional OCR engines. This is particularly the case for lexical data (i.e. words).		* Azure OCR's machine print recognition is generally as good or better than traditional OCR engines. This is particularly the case for lexical data (i.e. words).

Dgreenwood: /* How Grooper overcomes Azure OCR drawbacks */

2025-01-10T20:59:39Z

How Grooper overcomes Azure OCR drawbacks

← Older revision		Revision as of 15:59, 10 January 2025
Line 80:		Line 80:

	The result of combining both '''''OCR Engines''''' is what Grooper will actually recognize from the document.		The result of combining both '''''OCR Engines''''' is what Grooper will actually recognize from the document.

			=== Azure OCR in a Docker container ===

			Azure AI services may be hosted in a [https://www.docker.com/resources/what-container/ Docker container]. This lets you "self-host" Azure OCR. It lets you use the same APIs available in Azure, but on-premises. Reasons to do this include compliance, security or other operational concerns.

			More information on deploying Azure AI services in containers can be found in Microsoft's [https://learn.microsoft.com/en-us/azure/ai-services/cognitive-services-container-support Azure AI containers overview].

			[[File:2024 Azure-OCR 01 03 01-DockerURL.png\|right\|600px]]
			When connecting to Azure AI Services hosted in a Docker container, you must enter the URL for the Azure AI container with the "vision" endpoint specified. The URL should look like this:
			<pre style="width:auto">http://<container ip-address>:5000/vision</pre>

			Be aware:
			* "vision" must be lower-case.
			* 5000 is the default port for the container.

	== How to ==		== How to ==

Dgreenwood: /* About */

2024-12-26T15:30:56Z

About

← Older revision		Revision as of 10:30, 26 December 2024
Line 23:		Line 23:

	Supported image types: JPEG, PNG, BMP, PDF, and TIFF		Supported image types: JPEG, PNG, BMP, PDF, and TIFF

			{\|class="fyi-box"
			\|
			'''FYI'''
			\|
			You will need an API key from Azure when setting up an '''OCR Profile''' that uses '''''Azure OCR'''''. If you do not have an API key and need some instructions on how to create one in Azure, visit the following link in our "Grooper and AI" article:
			: [[Grooper and AI#Azure OCR Quickstart\|Azure OCR Quickstart]]
			\|}

	=== Azure OCR strengths over traditional OCR ===		=== Azure OCR strengths over traditional OCR ===

Dgreenwood: /* About */

2024-12-17T19:12:47Z

About

← Older revision		Revision as of 14:12, 17 December 2024
Line 21:		Line 21:

	Grooper attempts to return the most accurate results from both the '''''Azure OCR''''' and the traditional '''OCR Engine'''.		Grooper attempts to return the most accurate results from both the '''''Azure OCR''''' and the traditional '''OCR Engine'''.

			Supported image types: JPEG, PNG, BMP, PDF, and TIFF

	=== Azure OCR strengths over traditional OCR ===		=== Azure OCR strengths over traditional OCR ===

Randallkinard at 16:49, 21 November 2024

2024-11-21T16:49:33Z

← Older revision		Revision as of 11:49, 21 November 2024
Line 125:		Line 125:

	[[File:2024 Azure-OCR 02 03 02.png]]		[[File:2024 Azure-OCR 02 03 02.png]]

	~~== Glossary ==~~

	~~<u><big>'''Activity'''</big></u>: {{#lst:Glossary\|Activity}}~~

	~~<u><big>'''Alignment'''</big></u>: {{#lst:Glossary\|Alignment}}~~

	~~<u><big>'''Batch'''</big></u>: {{#lst:Glossary\|Batch}}~~

	~~<u><big>'''Batch Process Step'''</big></u>: {{#lst:Glossary\|Batch Process Step}}~~

	~~<u><big>'''Batch Process'''</big></u>: {{#lst:Glossary\|Batch Process}}~~

	~~<u><big>'''Image Processing'''</big></u>: {{#lst:Glossary\|Image Processing Concept}}~~

	~~<u><big>'''Image Processing'''</big></u>: {{#lst:Glossary\|Image Processing}}~~

	~~<u><big>'''IP Profile'''</big></u>: {{#lst:Glossary\|IP Profile}}~~

	~~<u><big>'''Labeled OMR'''</big></u>: {{#lst:Glossary\|Labeled OMR}}~~

	~~<u><big>'''Labeled Value'''</big></u>: {{#lst:Glossary\|Labeled Value}}~~

	~~<u><big>'''Node Tree'''</big></u>: {{#lst:Glossary\|Node Tree}}~~

	~~<u><big>'''OCR'''</big></u>: {{#lst:Glossary\|OCR}}~~

	~~<u><big>'''OCR Engine'''</big></u>: {{#lst:Glossary\|OCR Engine}}~~

	~~<u><big>'''OCR Profile'''</big></u>: {{#lst:Glossary\|OCR Profile}}~~

	~~<u><big>'''Project'''</big></u>: {{#lst:Glossary\|Project}}~~

	~~<u><big>'''Recognize'''</big></u>: {{#lst:Glossary\|Recognize}}~~

	~~<u><big>'''Scope'''</big></u>: {{#lst:Glossary\|Scope}}~~

	~~<u><big>'''Tabular Layout'''</big></u>: {{#lst:Glossary\|Tabular Layout}}~~

Dgreenwood: /* Adding the OCR Profile to the Recognize Step */

2024-10-04T21:14:13Z

Adding the OCR Profile to the Recognize Step

← Older revision		Revision as of 16:14, 4 October 2024
Line 111:		Line 111:
	[[File:2024 Azure-OCR 02 02 02.png]]		[[File:2024 Azure-OCR 02 02 02.png]]

	=== Adding the OCR Profile to the Recognize ~~Step~~ ===		=== Adding the OCR Profile to the Recognize step ===

	You will need to add a '''Batch Process Step''' configured with the ''Recognize Activity'' to your '''Batch Process'''. ~~You will also need to configure~~ the Step Properties ~~such as~~ the '''''Activity''''' and '''''Scope'''''. For help with setting up your '''Batch Process''', take a look at our [[Batch Process]] article.		You will need to add a '''Batch Process Step''' configured with the '''''Recognize Activity''''' to your '''Batch Process'''. In the '''''Step Properties''''', ensure the '''''Activity''''' is set to '''''Recognize''''' and the '''''Scope''''' is appropriate for your processing level. For help with setting up your '''Batch Process''', take a look at our [[Batch Process]] article.

	# Add and select the '''Recognize ~~Step~~''' in your '''Batch Process''' in the Node Tree.		# Add and select the '''''Recognize''''' step in your '''Batch Process''' in the Node Tree.
	# Click on the hamburger icon to the right of the '''''OCR Profile''''' property to access the navigation drop down.		# Click on the hamburger icon to the right of the '''''OCR Profile''''' property to access the navigation drop down.
	# Navigate to and select the '''OCR Profile''' that has been configured with the '''''Azure OCR''''' ~~'''''OCR Engine'''''~~.		# Navigate to and select the '''OCR Profile''' that has been configured with the '''''Azure OCR''''' engine.

	[[File:2024 Azure-OCR 02 03 01.png]]		[[File:2024 Azure-OCR 02 03 01.png]]


	#<li value=4> Finish configuring your '''Batch Process Step''' and then click the save icon located in the top right of the Step Properties property grid to save your changes.		#<li value=4> Finish configuring your '''Batch Process Step''' and then click the save icon located in the top right of the '''''Step Properties''''' property grid to save your changes.

	[[File:2024 Azure-OCR 02 03 02.png]]		[[File:2024 Azure-OCR 02 03 02.png]]

← Older revision		Revision as of 11:49, 21 November 2024
Line 125:		Line 125:

	[[File:2024 Azure-OCR 02 03 02.png]]		[[File:2024 Azure-OCR 02 03 02.png]]

	~~== Glossary ==~~

	~~<u><big>'''Activity'''</big></u>: {{#lst:Glossary\|Activity}}~~

	~~<u><big>'''Alignment'''</big></u>: {{#lst:Glossary\|Alignment}}~~

	~~<u><big>'''Batch'''</big></u>: {{#lst:Glossary\|Batch}}~~

	~~<u><big>'''Batch Process Step'''</big></u>: {{#lst:Glossary\|Batch Process Step}}~~

	~~<u><big>'''Batch Process'''</big></u>: {{#lst:Glossary\|Batch Process}}~~

	~~<u><big>'''Image Processing'''</big></u>: {{#lst:Glossary\|Image Processing Concept}}~~

	~~<u><big>'''Image Processing'''</big></u>: {{#lst:Glossary\|Image Processing}}~~

	~~<u><big>'''IP Profile'''</big></u>: {{#lst:Glossary\|IP Profile}}~~

	~~<u><big>'''Labeled OMR'''</big></u>: {{#lst:Glossary\|Labeled OMR}}~~

	~~<u><big>'''Labeled Value'''</big></u>: {{#lst:Glossary\|Labeled Value}}~~

	~~<u><big>'''Node Tree'''</big></u>: {{#lst:Glossary\|Node Tree}}~~

	~~<u><big>'''OCR'''</big></u>: {{#lst:Glossary\|OCR}}~~

	~~<u><big>'''OCR Engine'''</big></u>: {{#lst:Glossary\|OCR Engine}}~~

	~~<u><big>'''OCR Profile'''</big></u>: {{#lst:Glossary\|OCR Profile}}~~

	~~<u><big>'''Project'''</big></u>: {{#lst:Glossary\|Project}}~~

	~~<u><big>'''Recognize'''</big></u>: {{#lst:Glossary\|Recognize}}~~

	~~<u><big>'''Scope'''</big></u>: {{#lst:Glossary\|Scope}}~~

	~~<u><big>'''Tabular Layout'''</big></u>: {{#lst:Glossary\|Tabular Layout}}~~