2023:OCR Synthesis (Concept) - Revision history

Randallkinard at 15:02, 22 November 2024

2024-11-22T15:02:19Z

← Older revision		Revision as of 10:02, 22 November 2024
Line 449:		Line 449:

	The reason behind this is how colons are used on documents. Typically, they themselves are used to break information out into meaningful segments. On the left side of the colon is some kind of label identifier. On the right followed by a gap is a piece of information that label pertains to. These labels are very important and the pieces of information they relate to are very important. Making sure both can be reprocessed independently tends to yield better OCR results and therefore data extraction down the line.		The reason behind this is how colons are used on documents. Typically, they themselves are used to break information out into meaningful segments. On the left side of the colon is some kind of label identifier. On the right followed by a gap is a piece of information that label pertains to. These labels are very important and the pieces of information they relate to are very important. Making sure both can be reprocessed independently tends to yield better OCR results and therefore data extraction down the line.

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

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

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

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

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

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

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

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

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

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

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

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

Randallkinard at 14:49, 27 August 2024

2024-08-27T14:49:55Z

@@ Line 12: / Line 12: @@
 * [[Media:2023_Wiki_OCR-Synthesis_Batch.zip]]
 |}
 == About ==
@@ Line 474: / Line 449: @@
 The reason behind this is how colons are used on documents. Typically, they themselves are used to break information out into meaningful segments. On the left side of the colon is some kind of label identifier. On the right followed by a gap is a piece of information that label pertains to. These labels are very important and the pieces of information they relate to are very important. Making sure both can be reprocessed independently tends to yield better OCR results and therefore data extraction down the line.

Randallkinard at 16:29, 10 May 2024

2024-05-10T16:29:16Z

@@ Line 12: / Line 12: @@
 * [[Media:2023_Wiki_OCR-Synthesis_Batch.zip]]
 |}
 == About ==

Randallkinard at 20:09, 23 April 2024

2024-04-23T20:09:18Z

← Older revision		Revision as of 15:09, 23 April 2024
Line 1:		Line 1:
	{{AutoVersion}}		{{AutoVersion}}
	~~<section begin="glossary" />~~
	<blockquote>		<blockquote>{{#lst:Glossary\|OCR Synthesis}}</blockquote>
	~~The '''''Synthesis''''' functionality is Grooper's unique method of pre-processing and re-processing raw results from the [[OCR Engine~~\|OCR ~~engine]] to get better results out of it.~~
	</blockquote>
	~~<section end="glossary" />~~
	Using '''''Synthesis''''', portions of the document can be OCR'd independently from the full text OCR. Portions of the image dropped out from the first OCR pass can be re-run through the OCR engine. And, certain results can be reprocessed. The results from the '''''Synthesis''''' operation are combined with (or in some cases replace) the full text OCR results from the OCR Engine into a single text flow.		Using '''''Synthesis''''', portions of the document can be OCR'd independently from the full text OCR. Portions of the image dropped out from the first OCR pass can be re-run through the OCR engine. And, certain results can be reprocessed. The results from the '''''Synthesis''''' operation are combined with (or in some cases replace) the full text OCR results from the OCR Engine into a single text flow.

Line 16:		Line 14:

	== About ==		== About ==

	'''''Synthesis''''' is a collection of five separate OCR processing operations:		'''''Synthesis''''' is a collection of five separate OCR processing operations:

Randallkinard: Randallkinard moved page 2023:OCR Synthesis to 2023:OCR Synthesis (Concept) without leaving a redirect: new naming convention

2024-04-16T20:43:06Z

Randallkinard moved page 2023:OCR Synthesis to 2023:OCR Synthesis (Concept) without leaving a redirect: new naming convention

← Older revision	Revision as of 15:43, 16 April 2024
(No difference)

Dgreenwood: /* About */

2024-03-26T20:59:36Z

About

← Older revision		Revision as of 15:59, 26 March 2024
Line 6:		Line 6:
	<section end="glossary" />		<section end="glossary" />
	Using '''''Synthesis''''', portions of the document can be OCR'd independently from the full text OCR. Portions of the image dropped out from the first OCR pass can be re-run through the OCR engine. And, certain results can be reprocessed. The results from the '''''Synthesis''''' operation are combined with (or in some cases replace) the full text OCR results from the OCR Engine into a single text flow.		Using '''''Synthesis''''', portions of the document can be OCR'd independently from the full text OCR. Portions of the image dropped out from the first OCR pass can be re-run through the OCR engine. And, certain results can be reprocessed. The results from the '''''Synthesis''''' operation are combined with (or in some cases replace) the full text OCR results from the OCR Engine into a single text flow.

	~~== About ==~~

	{\|class="download-box"		{\|class="download-box"
Line 16:		Line 14:
	* [[Media:2023_Wiki_OCR-Synthesis_Batch.zip]]		* [[Media:2023_Wiki_OCR-Synthesis_Batch.zip]]
	\|}		\|}

			== About ==

	'''''Synthesis''''' is a collection of five separate OCR processing operations:		'''''Synthesis''''' is a collection of five separate OCR processing operations:

Randallkinard: done // via Wikitext Extension for VSCode

2024-03-08T20:38:25Z

done // via Wikitext Extension for VSCode

Show changes

Randallkinard: testing // via Wikitext Extension for VSCode

2024-03-08T19:58:13Z

testing // via Wikitext Extension for VSCode

← Older revision		Revision as of 14:58, 8 March 2024
Line 177:		Line 177:

	==== Properties affecting box size and detection ====		==== Properties affecting box size and detection ====
	~~<table~~ cellpadding="10" cellspacing="5" style="margin:auto">		{\|cellpadding=10 cellspacing=5 style="margin:auto"
	~~<tr~~ style="background-color:#36B0A7; color:white">		\|-style="background-color:#36B0A7; color:white"
	~~<td~~ style="width:17%"~~><b>~~Property~~</b>~~		\|style="width:17%"\|'''Property'''
	~~</td>~~		\|style="width:17%"\|'''Default Value'''
	~~<td~~ style="width:17%"~~><b>~~Default Value~~</b>~~		\|'''Information'''
	~~</td>~~		\|-style="background-color:#ddf5f5"
	~~<td><b>~~Information~~</b>~~		\|Minimum Size\|\|6pt\|\|This setting controls the minimum width or height of a box. So, the default box size will detect a minimum of a box 6 pt wide by 1 pt high or 1 pt wide by 6 pt high. That is a fairly small box. If Image Segmentation is detecting bound regions that aren't boxes, you may find it useful to increase the size of this property.
	~~</td></tr>~~		\|-style="background-color:#ddf5f5"
	~~<tr~~ style="background-color:#ddf5f5">		\|Minimum Area\|\|12pt\|\|This setting controls the minimum area of a box. This works in combination with the "Minimum Size" property to control which boxes are detected. So, even though the Minimum Size default is 6 pt, Image Segmentation won't actually detect a 6 pt wide by 1 pt high box, because its area is only 6 pt (6 x 1 = 6 and 6 < 12). Similarly this property is helpful to narrow down which bound regions should be included in the Image Segmentation operation.
	~~<td>~~Minimum Size~~</td>~~		\|-style="background-color:#ddf5f5"
	~~<td>~~6pt~~</td>~~		\|Maximum Width Ratio\|\|75%\|\|This property controls the maximum width of a single box based on it's size corresponding to the whole page. At 75%, a single box will not be detected if it is larger than three quarters of the width of the whole page. If you want to detect boxes of any width, even if they span the full width of the page, you will set this property to 100%.
	~~<td>~~This setting controls the minimum width or height of a box. So, the default box size will detect a minimum of a box 6 pt wide by 1 pt high or 1 pt wide by 6 pt high. That is a fairly small box. If Image Segmentation is detecting bound regions that aren't boxes, you may find it useful to increase the size of this property.		\|-style="background-color:#ddf5f5"
	~~</td></tr>~~		\|Maximum Height\|\|1in\|\|Here, you can limit the maximum height of a box. If you wish to detect boxes of any height, change this property to "0". This property also interacts with the "Always Allow Landscape" property. See below for important information on how they interact.
	~~<tr~~ style="background-color:#ddf5f5">		\|-style="background-color:#ddf5f5"
	~~<td>~~Minimum Area~~</td>~~		\|Always Allow Landscape\|\|True\|\|By default, boxes that are longer than they are high (having a "landscape" instead of "portrait" orientation) are ''exempted'' from exclusion if they are higher than the the "Maximum Height" value. Only boxes that are narrower than they are high ("portrait" orriented boxes) will be excluded from Image Segmentation. If you are attempting to remove boxes that are longer than they are high from processing using the "Maximum Height" value, set this property to "False".
	~~<td>~~12pt~~</td>~~		\|-style="background-color:#ddf5f5"
	~~<td>~~This setting controls the minimum area of a box. This works in combination with the "Minimum Size" property to control which boxes are detected. So, even though the Minimum Size default is 6 pt, Image Segmentation won't actually detect a 6 pt wide by 1 pt high box, because its area is only 6 pt (6 x 1 = 6 and 6 ~~<~~ 12). Similarly this property is helpful to narrow down which bound regions should be included in the Image Segmentation operation.		\|Maximum Count\|\|0\|\|With this property set to "0" there will be no limit to the number of boxes detected. If you do enter a maximum count value, bound region detection will stop once it finds one less than the maximum value (i.e. If you enter a Maximum Count of "10" and there are 11 boxes on the page, only 9 bound regions will be detected.)
	~~</td></tr>~~		\|}
	~~<tr~~ style="background-color:#ddf5f5">
	~~<td>~~Maximum Width Ratio~~</td>~~
	~~<td>~~75%~~</td>~~
	~~<td>~~This property controls the maximum width of a single box based on it's size corresponding to the whole page. At 75%, a single box will not be detected if it is larger than three quarters of the width of the whole page. If you want to detect boxes of any width, even if they span the full width of the page, you will set this property to 100%.
	~~</td></tr>~~
	~~<tr~~ style="background-color:#ddf5f5">
	~~<td>~~Maximum Height~~</td>~~
	~~<td>~~1in~~</td>~~
	~~<td>~~Here, you can limit the maximum height of a box. If you wish to detect boxes of any height, change this property to "0". This property also interacts with the "Always Allow Landscape" property. See below for important information on how they interact.
	~~</td></tr>~~
	~~<tr~~ style="background-color:#ddf5f5">
	~~<td>~~Always Allow Landscape~~</td>~~
	~~<td>~~True~~</td>~~
	~~<td>~~By default, boxes that are longer than they are high (having a "landscape" instead of "portrait" orientation) are ~~<i>~~exempted~~</i>~~ from exclusion if they are higher than the the "Maximum Height" value. Only boxes that are narrower than they are high ("portrait" orriented boxes) will be excluded from Image Segmentation. If you are attempting to remove boxes that are longer than they are high from processing using the "Maximum Height" value, set this property to "False".
	~~</td></tr>~~
	~~<tr~~ style="background-color:#ddf5f5">
	~~<td>~~Maximum Count~~</td>~~
	~~<td>~~0~~</td>~~
	~~<td>~~With this property set to "0" there will be no limit to the number of boxes detected. If you do enter a maximum count value, bound region detection will stop once it finds one less than the maximum value (i.e. If you enter a Maximum Count of "10" and there are 11 boxes on the page, only 9 bound regions will be detected.)
	~~</td></tr></table>~~

	==== The Merge Regions property ====		==== The Merge Regions property ====

Randallkinard: testing // via Wikitext Extension for VSCode

2024-03-08T19:49:42Z

testing // via Wikitext Extension for VSCode

← Older revision		Revision as of 14:49, 8 March 2024
Line 178:		Line 178:
	==== Properties affecting box size and detection ====		==== Properties affecting box size and detection ====
	<table cellpadding="10" cellspacing="5" style="margin:auto">		<table cellpadding="10" cellspacing="5" style="margin:auto">
	~~<tbody>~~<tr style="background-color:#36B0A7; color:white">		<tr style="background-color:#36B0A7; color:white">
	<td style="width:17%"><b>Property</b>		<td style="width:17%"><b>Property</b>
	</td>		</td>
Line 214:		Line 214:
	<td>0</td>		<td>0</td>
	<td>With this property set to "0" there will be no limit to the number of boxes detected. If you do enter a maximum count value, bound region detection will stop once it finds one less than the maximum value (i.e. If you enter a Maximum Count of "10" and there are 11 boxes on the page, only 9 bound regions will be detected.)		<td>With this property set to "0" there will be no limit to the number of boxes detected. If you do enter a maximum count value, bound region detection will stop once it finds one less than the maximum value (i.e. If you enter a Maximum Count of "10" and there are 11 boxes on the page, only 9 bound regions will be detected.)
	</td></tr~~></tbody~~></table>		</td></tr></table>

	==== The Merge Regions property ====		==== The Merge Regions property ====

Randallkinard: testing ... // via Wikitext Extension for VSCode

2024-03-08T19:48:54Z

testing ... // via Wikitext Extension for VSCode

Show changes

← Older revision		Revision as of 10:02, 22 November 2024
Line 449:		Line 449:

	The reason behind this is how colons are used on documents. Typically, they themselves are used to break information out into meaningful segments. On the left side of the colon is some kind of label identifier. On the right followed by a gap is a piece of information that label pertains to. These labels are very important and the pieces of information they relate to are very important. Making sure both can be reprocessed independently tends to yield better OCR results and therefore data extraction down the line.		The reason behind this is how colons are used on documents. Typically, they themselves are used to break information out into meaningful segments. On the left side of the colon is some kind of label identifier. On the right followed by a gap is a piece of information that label pertains to. These labels are very important and the pieces of information they relate to are very important. Making sure both can be reprocessed independently tends to yield better OCR results and therefore data extraction down the line.

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

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

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

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

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

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

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

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

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

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

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

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