Azure DI OCR (OCR Engine) - Revision history

Dgreenwood: /* OCR Data Alignment */

2026-03-18T19:56:49Z

OCR Data Alignment

← Older revision		Revision as of 14:56, 18 March 2026
Line 54:		Line 54:
	Grooper's unique OCR synthesis approach further improves Azure's OCR capabilities. We use traditional OCR engines and computer vision to enhance the final output, mitigating known limitations in Azure's Read engine and producing more accurate extraction than any single OCR engine alone.		Grooper's unique OCR synthesis approach further improves Azure's OCR capabilities. We use traditional OCR engines and computer vision to enhance the final output, mitigating known limitations in Azure's Read engine and producing more accurate extraction than any single OCR engine alone.

	[[#How Azure DI OCR ~~Utilizes~~ the OCR Data Aligner\| See "How Azure DI OCR ~~Utilizes~~ the OCR Data Aligner" for more]]		[[#How Azure DI OCR utilizes the OCR Data Aligner\| See "How Azure DI OCR utilizes the OCR Data Aligner" for more]]

	== About Document Intelligence models ==		== About Document Intelligence models ==

Dgreenwood: /* How Azure DI OCR Utilizes the OCR Data Aligner */

2026-03-18T19:56:33Z

How Azure DI OCR Utilizes the OCR Data Aligner

← Older revision		Revision as of 14:56, 18 March 2026
Line 219:		Line 219:
	'''UNDER DEVELOPMENT:''' This parameter is present in the Grooper property grid but is not fully implemented. Enabling this feature will do nothing at this time and is likely to throw an error.		'''UNDER DEVELOPMENT:''' This parameter is present in the Grooper property grid but is not fully implemented. Enabling this feature will do nothing at this time and is likely to throw an error.

	== How Azure DI OCR ~~Utilizes~~ the OCR Data Aligner ==		== How Azure DI OCR utilizes the OCR Data Aligner ==

	A unique feature of Grooper’s Azure DI OCR implementation is the use of the "OCR Data Aligner". This component coordinates the alignment and correction of OCR results between Azure Document Intelligence and Grooper’s internal OCR engines (such as Transym or Tesseract).		A unique feature of Grooper’s Azure DI OCR implementation is the use of the "OCR Data Aligner". This component coordinates the alignment and correction of OCR results between Azure Document Intelligence and Grooper’s internal OCR engines (such as Transym or Tesseract).

Dgreenwood: /* Azure DI OCR and Grooper's OCR Synthesis */

2026-03-18T19:56:17Z

Azure DI OCR and Grooper's OCR Synthesis

← Older revision		Revision as of 14:56, 18 March 2026
Line 50:		Line 50:
	**<li class="fyi-bullet"> Azure DI OCR offers the best OMR checkbox detection in Grooper to date.		**<li class="fyi-bullet"> Azure DI OCR offers the best OMR checkbox detection in Grooper to date.

	=== ~~Azure DI~~ OCR ~~and Grooper's OCR Synthesis~~ ===		=== OCR Data Alignment ===

	Grooper's unique OCR synthesis approach further improves Azure's OCR capabilities. We use traditional OCR engines and computer vision to enhance the final output, mitigating known limitations in Azure's Read engine and producing more accurate extraction than any single OCR engine alone.		Grooper's unique OCR synthesis approach further improves Azure's OCR capabilities. We use traditional OCR engines and computer vision to enhance the final output, mitigating known limitations in Azure's Read engine and producing more accurate extraction than any single OCR engine alone.

			[[#How Azure DI OCR Utilizes the OCR Data Aligner\| See "How Azure DI OCR Utilizes the OCR Data Aligner" for more]]

	== About Document Intelligence models ==		== About Document Intelligence models ==

Dgreenwood: /* What is Azure DI OCR? */

2026-03-18T19:54:32Z

What is Azure DI OCR?

← Older revision		Revision as of 14:54, 18 March 2026
Line 49:		Line 49:
	* '''Advanced Layout Detection''': Beyond text, Azure DI OCR can detect checkboxes and barcodes, supporting complex extraction scenarios.		* '''Advanced Layout Detection''': Beyond text, Azure DI OCR can detect checkboxes and barcodes, supporting complex extraction scenarios.
	**<li class="fyi-bullet"> Azure DI OCR offers the best OMR checkbox detection in Grooper to date.		**<li class="fyi-bullet"> Azure DI OCR offers the best OMR checkbox detection in Grooper to date.

			=== Azure DI OCR and Grooper's OCR Synthesis ===

			Grooper's unique OCR synthesis approach further improves Azure's OCR capabilities. We use traditional OCR engines and computer vision to enhance the final output, mitigating known limitations in Azure's Read engine and producing more accurate extraction than any single OCR engine alone.

	== About Document Intelligence models ==		== About Document Intelligence models ==

Dgreenwood: /* Barcodes */

2026-01-15T21:07:43Z

Barcodes

← Older revision		Revision as of 16:07, 15 January 2026
Line 139:		Line 139:
	Incurs additional cost in Azure? '''No'''		Incurs additional cost in Azure? '''No'''

	'''Azure DI OCR''' stores detected barcodes in the Grooper [[Layout Data]] file (Grooper.~~LayoutData~~.json) created during Recognize. This extends barcode data to all mechanisms Grooper uses to evaluate and return barcodes from layout data, such as the [[Find Barcode]] extractor.		'''Azure DI OCR''' stores detected barcodes in the Grooper [[Layout Data]] file (Grooper.Layout.json) created during Recognize. This extends barcode data to all mechanisms Grooper uses to evaluate and return barcodes from layout data, such as the [[Find Barcode]] extractor.

	Supported barcode types:		Supported barcode types:

Dgreenwood: /* Add-on features relevant to Azure DI OCR */

2026-01-15T21:07:09Z

Add-on features relevant to Azure DI OCR

← Older revision		Revision as of 16:07, 15 January 2026
Line 125:		Line 125:

	:'''Relevant to Azure DI OCR''' - Enabling these features will affect results Azure DI OCR produces		:'''Relevant to Azure DI OCR''' - Enabling these features will affect results Azure DI OCR produces
	:* Barcodes - ''Impacts the Grooper layout data Recognize generates (Grooper.~~LayoutData~~.json)''		:* Barcodes - ''Impacts the Grooper layout data Recognize generates (Grooper.Layout.json)''
	:* OCR High Resolution - ''Impacts the Grooper text data Recognize generates (Grooper.Characters.txt)''		:* OCR High Resolution - ''Impacts the Grooper text data Recognize generates (Grooper.Characters.txt)''

Dgreenwood: /* Add-on features */

2026-01-15T21:06:05Z

Add-on features

← Older revision		Revision as of 16:06, 15 January 2026
Line 111:		Line 111:

	[[File:2025-AzureDIOCR-Features.png\|thumb\|right\|400px\|The Document Intelligence add-ons are enabled in the Features properties in Grooper.]]		[[File:2025-AzureDIOCR-Features.png\|thumb\|right\|400px\|The Document Intelligence add-ons are enabled in the Features properties in Grooper.]]
	In Grooper, these add-ons can be enabled in the Azure DI OCR engine's set of ''Features'' properties.		In Grooper, these add-ons can be enabled in the Azure DI OCR engine's set of '''Features''' properties.
	*<li class="attn-bullet"> Not all models can utilize every add-on. For more information see Azure's [https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/model-overview?view=#model-analysis-features model overview documentation]. Add-on features unsupported by the Read model are documented below.		*<li class="attn-bullet"> Not all models can utilize every add-on. For more information see Azure's [https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/model-overview?view=#model-analysis-features model overview documentation]. Add-on features unsupported by the Read model are documented below.

Dgreenwood: /* What is Azure DI OCR? */

2026-01-15T18:04:37Z

What is Azure DI OCR?

← Older revision		Revision as of 13:04, 15 January 2026
Line 25:		Line 25:
	'''Azure DI OCR''' is an [[OCR Engine]] in Grooper that leverages text recognition models in an Azure Document Intelligence service.		'''Azure DI OCR''' is an [[OCR Engine]] in Grooper that leverages text recognition models in an Azure Document Intelligence service.
	* It is designed to recognize machine print and handwritten text from scanned documents, forms and images.		* It is designed to recognize machine print and handwritten text from scanned documents, forms and images.
	* It recognizes checkboxes and barcodes innately (no IP Profile necessary).
	**<li class="fyi-bullet"> Grooper IP is still needed to detect line segments (such as table lines). However, Grooper's Line Detection runs alongside Document Intelligence thanks to Azure DI OCR's [[#How Azure DI OCR Utilizes the OCR Data Aligner\|OCR Data Aligner]].
	* Multiple languages are supported.		* Multiple languages are supported.
	* Azure DI OCR further improves Document Intelligence's results by aligning and correcting OCR results with Grooper's internal OCR engines.		* Azure DI OCR further improves Document Intelligence's results by aligning and correcting OCR results with Grooper's internal OCR engines.
			* When configured appropriately, it recognizes checkboxes and barcodes innately (no IP Profile necessary).
			**<li class="fyi-bullet"> Grooper IP is still needed to detect line segments (such as table lines). However, Grooper's Line Detection runs alongside Document Intelligence thanks to Azure DI OCR's [[#How Azure DI OCR Utilizes the OCR Data Aligner\|OCR Data Aligner]].

	=== Connecting Grooper to a Document Intelligence resource in Azure ===		=== Connecting Grooper to a Document Intelligence resource in Azure ===

Dgreenwood: /* What is Azure DI OCR? */

2026-01-15T18:03:36Z

What is Azure DI OCR?

← Older revision		Revision as of 13:03, 15 January 2026
Line 26:		Line 26:
	* It is designed to recognize machine print and handwritten text from scanned documents, forms and images.		* It is designed to recognize machine print and handwritten text from scanned documents, forms and images.
	* It recognizes checkboxes and barcodes innately (no IP Profile necessary).		* It recognizes checkboxes and barcodes innately (no IP Profile necessary).
	**<li class="fyi-bullet"> Grooper IP is still needed to detect line segments (such as table lines). However, Grooper's Line Detection runs alongside Document Intelligence thanks to Azure DI OCR's ~~"Character~~ Data ~~Alignment"~~.		**<li class="fyi-bullet"> Grooper IP is still needed to detect line segments (such as table lines). However, Grooper's Line Detection runs alongside Document Intelligence thanks to Azure DI OCR's [[#How Azure DI OCR Utilizes the OCR Data Aligner\|OCR Data Aligner]].
	* Multiple languages are supported.		* Multiple languages are supported.
	* Azure DI OCR further improves Document Intelligence's results by aligning and correcting OCR results with Grooper's internal OCR engines.		* Azure DI OCR further improves Document Intelligence's results by aligning and correcting OCR results with Grooper's internal OCR engines.

Dgreenwood: /* What is Azure DI OCR? */

2026-01-15T18:02:15Z

What is Azure DI OCR?

← Older revision		Revision as of 13:02, 15 January 2026
Line 26:		Line 26:
	* It is designed to recognize machine print and handwritten text from scanned documents, forms and images.		* It is designed to recognize machine print and handwritten text from scanned documents, forms and images.
	* It recognizes checkboxes and barcodes innately (no IP Profile necessary).		* It recognizes checkboxes and barcodes innately (no IP Profile necessary).
			**<li class="fyi-bullet"> Grooper IP is still needed to detect line segments (such as table lines). However, Grooper's Line Detection runs alongside Document Intelligence thanks to Azure DI OCR's "Character Data Alignment".
	* Multiple languages are supported.		* Multiple languages are supported.
	* Azure DI OCR further improves Document Intelligence's results by aligning and correcting OCR results with Grooper's internal OCR engines.		* Azure DI OCR further improves Document Intelligence's results by aligning and correcting OCR results with Grooper's internal OCR engines.