2.80:Shape Removal (IP Command) - Revision history

Dgreenwood at 15:12, 5 August 2025

2025-08-05T15:12:53Z

← Older revision		Revision as of 10:12, 5 August 2025
Line 1:		Line 1:
			__NOINDEX__
	{{AutoVersion}}		{{AutoVersion}}

Randallkinard at 15:19, 29 April 2024

2024-04-29T15:19:07Z

← Older revision		Revision as of 10:19, 29 April 2024
Line 1:		Line 1:
	{{AutoVersion}}		{{AutoVersion}}

	[[image:1573840802890-595.png\|frame]]		[[image:1573840802890-595.png\|frame]]

	<blockquote ~~style="font-size~~:~~14pt">~~		<blockquote>{{#lst:Glossary\|Shape Removal}}</blockquote>
	~~'''~~Shape Removal~~''' detects and removes shapes from documents.~~
	</blockquote>

	The Shape Removal command builds upon the existing Shape Detection command. Shape Detection finds shapes in a document (such as logos) from a set of sample images given by the user. Shape Removal goes one step further and removes the detected shape from the document. The removed pixels are either filled in with a solid color or inpainted to try and match it to pixels nearby.		The Shape Removal command builds upon the existing Shape Detection command. Shape Detection finds shapes in a document (such as logos) from a set of sample images given by the user. Shape Removal goes one step further and removes the detected shape from the document. The removed pixels are either filled in with a solid color or inpainted to try and match it to pixels nearby.

Randallkinard: Randallkinard moved page 2.80:Shape Removal to 2.80:Shape Removal (IP Command) without leaving a redirect: new naming convention

2024-04-18T16:33:50Z

Randallkinard moved page 2.80:Shape Removal to 2.80:Shape Removal (IP Command) without leaving a redirect: new naming convention

← Older revision	Revision as of 11:33, 18 April 2024
(No difference)

Dgreenwood: Dgreenwood moved page Shape Removal - 2.80 to 2.80:Shape Removal without leaving a redirect

2024-01-03T16:11:13Z

Dgreenwood moved page Shape Removal - 2.80 to 2.80:Shape Removal without leaving a redirect

← Older revision	Revision as of 11:11, 3 January 2024
(No difference)

Dgreenwood at 16:11, 3 January 2024

2024-01-03T16:11:03Z

← Older revision		Revision as of 11:11, 3 January 2024
Line 1:		Line 1:
			{{AutoVersion}}
	[[image:1573840802890-595.png\|frame]]		[[image:1573840802890-595.png\|frame]]

Line 490:		Line 491:
	[[image:1574788850180-109.png]]		[[image:1574788850180-109.png]]
	\|}		\|}

	~~[[Category:Articles]]~~
	~~[[Category:Version 2.80]]~~

Dgreenwood: /* Dropout Method Details */

2022-12-12T21:31:24Z

Dropout Method Details

← Older revision		Revision as of 16:31, 12 December 2022
Line 476:		Line 476:
	{\|cellspacing="5" cellpadding="10"		{\|cellspacing="5" cellpadding="10"
	\|-		\|-
	\|The "Fill" method replaces dropped out pixels with a given color. The "Fill Color" property determines what color is used to fill the pixels. It defaults to a color determined to match the image's background. Alternatively, you can pick which color to fill the pixels. The "Mask Dilation Factor" will dilate the filled shape. Colored pixels will be added to the shape's borders, increasing the size of the removed area.\|\|[[image:1574789500411-585.png]]		\|style="width:60%"\|
			The "Fill" method replaces dropped out pixels with a given color. The "Fill Color" property determines what color is used to fill the pixels. It defaults to a color determined to match the image's background. Alternatively, you can pick which color to fill the pixels. The "Mask Dilation Factor" will dilate the filled shape. Colored pixels will be added to the shape's borders, increasing the size of the removed area.
			\|
			[[image:1574789500411-585.png]]
	\|-		\|-
	\|"Inpaint" fills the dropout mask using color information from pixels around the removed pixels. This method is designed to match removed pixels to a colored or complex background. Student transcripts are a great example. They often are printed on paper with some kind of patterned background. There are two "Inpaint Method" options: Telea and NavierStokes.		\|"Inpaint" fills the dropout mask using color information from pixels around the removed pixels. This method is designed to match removed pixels to a colored or complex background. Student transcripts are a great example. They often are printed on paper with some kind of patterned background. There are two "Inpaint Method" options: Telea and NavierStokes.
Line 484:		Line 487:

	The "Inpaint Radius" property specifies how large the area around the dropped out pixels Grooper is "looking at" to get a picture of how to fill it in. It increases the size of the analyzed "neighborhood" of pixels. The "Mask Dilation Factor" will dilate the filled shape. Colored pixels will be added to the shape's borders, increasing the size of the removed area.		The "Inpaint Radius" property specifies how large the area around the dropped out pixels Grooper is "looking at" to get a picture of how to fill it in. It increases the size of the analyzed "neighborhood" of pixels. The "Mask Dilation Factor" will dilate the filled shape. Colored pixels will be added to the shape's borders, increasing the size of the removed area.
	\|[[image:1574788850180-109.png]]		\|
			[[image:1574788850180-109.png]]
	\|}		\|}

	[[Category:Articles]]		[[Category:Articles]]
	[[Category:Version 2.80]]		[[Category:Version 2.80]]

Dgreenwood at 19:07, 12 December 2022

2022-12-12T19:07:50Z

← Older revision		Revision as of 14:07, 12 December 2022
Line 486:		Line 486:
	\|[[image:1574788850180-109.png]]		\|[[image:1574788850180-109.png]]
	\|}		\|}

			[[Category:Articles]]
			[[Category:Version 2.80]]

Dgreenwood: Dgreenwood moved page Shape Removal to Shape Removal - 2.80: To be consistent with current naming conventions

2022-12-12T19:07:25Z

Dgreenwood moved page Shape Removal to Shape Removal - 2.80: To be consistent with current naming conventions

← Older revision	Revision as of 14:07, 12 December 2022
(No difference)

Configadmin at 16:03, 26 December 2019

2019-12-26T16:03:32Z

Show changes

Configadmin: /* How To: Add Shape Removal to an IP Profile */

2019-12-26T15:44:53Z

How To: Add Shape Removal to an IP Profile

← Older revision		Revision as of 10:44, 26 December 2019
Line 202:		Line 202:
	As you can see, we have a problem. While the Shape Mask looks like a slightly blurry silloute of our sample image (we'll talk about why it's blurry later), the Dropout Mask does not contain the three scales underneath the "G". Only pixels from the dropout mask are removed, giving us a poor result.		As you can see, we have a problem. While the Shape Mask looks like a slightly blurry silloute of our sample image (we'll talk about why it's blurry later), the Dropout Mask does not contain the three scales underneath the "G". Only pixels from the dropout mask are removed, giving us a poor result.

	{\|style="text-align:center"		{\|style="text-align:center; margin:auto"
			\|-valign="top"
	\|Shape Mask		\|Shape Mask

	[[image:1573854464807-645.png\|center]]		[[image:1573854464807-645.png\|\|border\|center\|250px]]
	\|Dropout Mask		\|Dropout Mask

	[[image:1573854469509-381.png\|center]]		[[image:1573854469509-381.png\|border\|center\|250px]]
	\|Result		\|Result

	[[image:1573854725419-945.png\|center]]		[[image:1573854725419-945.png\|border\|center\|250px]]
	\|}		\|}

Line 251:		Line 252:
	Importantly, the document is not permanently binarized. It is only temporarily turned black and white to figure out which pixels to remove. Recall from the previous step, the scales below the "G" in the Grooper logo were not removed. This is because the threshold determined by the default "Auto" setting was too low. Those pixels were determined to be more intense than the automatically determined threshold of 140. If we increase the threshold to 200, these pixels' intensity will fall below the the threshold and be converted to black, as seen below.		Importantly, the document is not permanently binarized. It is only temporarily turned black and white to figure out which pixels to remove. Recall from the previous step, the scales below the "G" in the Grooper logo were not removed. This is because the threshold determined by the default "Auto" setting was too low. Those pixels were determined to be more intense than the automatically determined threshold of 140. If we increase the threshold to 200, these pixels' intensity will fall below the the threshold and be converted to black, as seen below.

	{\|style="text-align:center"		{\|style="text-align:center; margin:auto" cellpadding="10" cellspacing="5"
	\|Threshold 140<br />[[image:1573854949963-402.png\|center\|400px]]\|\|Threshold 200<br />[[image:1574090625722-854.png\|center\|400px]]		\|Threshold 140<br />[[image:1573854949963-402.png\|center\|400px]]\|\|Threshold 200<br />[[image:1574090625722-854.png\|center\|400px]]
	\|}		\|}
Line 304:		Line 305:
	This property expands the dropout mask to increase the region of pixels to fill.		This property expands the dropout mask to increase the region of pixels to fill.

	{\|style="text-align:center"
			{\|style="text-align:center; margin:auto" cellpadding="10" cellspacing="5"
	\|-		\|-
	\|No Mask Dilation Factor\|\|Mask Dilation Factor of "6". No more logo!		\|No Mask Dilation Factor\|\|Mask Dilation Factor of "6". No more logo!
	\|-		\|-
	\|[[image:1574092055626-951.png]]\|[[image:1574092067563-404.png]]		\|[[image:1574092055626-951.png\|border]]\|\|[[image:1574092067563-404.png\|border]]
	\|}		\|}

	{\|cellpadding="10" cellspacing="5" style="background-color:#36b0a7; color:white"
	\|'''FYI'''\|\|This property can be to a whole number from -16 to 16. Where a positive number dilates the dropout mask, a negative number will erode it. Rather than increasing the region of pixels filled, it will decrease it. Below is the same logo with a dilation factor of -6.		{\|cellpadding="10" cellspacing="5"
			\|-style="background-color:#36b0a7; color:white"
			\|style="font-size:16pt"\|'''FYI'''\|\|This property can be to a whole number from -16 to 16. Where a positive number dilates the dropout mask, a negative number will erode it. Rather than increasing the region of pixels filled, it will decrease it. Below is the same logo with a dilation factor of -6.


Line 324:		Line 328:


	{\|cellpadding="10" cellspacing="5"		{\|cellpadding="10" cellspacing="5" style="margin:auto"
	\|-~~valign="top"~~		\|-
	\|[[image:1574092826663-971.png\|center]]\|\|Remember, there is a small halo of pixels around the dropout out mask that were turned white when binarized and thus not included in the dropout mask. Since these colored pixels are right next to the dropped out pixels, they are included in the pixel information used to fill the void from removing the dropout mask.		\|[[image:1574092826663-971.png\|center\|border]]\|\|Remember, there is a small halo of pixels around the dropout out mask that were turned white when binarized and thus not included in the dropout mask. Since these colored pixels are right next to the dropped out pixels, they are included in the pixel information used to fill the void from removing the dropout mask.
	\|-~~valign="top"~~		\|-
	\|[[image:1574093053596-905.png\|center]]\|\|Much like we resolved the issue by dilating the dropout mask, we can set the "Mask Dilation Factor" (Set to "6" here) to bloat the dropout mask's size, effectively passing over most of these pixels. Note, it does not entirely turn the area white because there are still light orange and green pixels in the neighborhood used to restore the dropped out area.		\|[[image:1574093053596-905.png\|center\|border]]\|\|Much like we resolved the issue by dilating the dropout mask, we can set the "Mask Dilation Factor" (Set to "6" here) to bloat the dropout mask's size, effectively passing over most of these pixels. Note, it does not entirely turn the area white because there are still light orange and green pixels in the neighborhood used to restore the dropped out area.
	\|}		\|}

Line 340:		Line 344:
	{\|style="text-align:center; margin:auto" cellpadding="10" cellspacing="5"		{\|style="text-align:center; margin:auto" cellpadding="10" cellspacing="5"
	\| \|\|3px Inpaint Radius\|\|25px Inpaint Radius		\| \|\|3px Inpaint Radius\|\|25px Inpaint Radius
	\|'''Telea'''\|\|[[image:1574097431794-254.png]]\|\|[[image:1574097438229-534.png]]		\|-
	\|'''NavierStokes'''\|\|[[image:1574097384241-326.png]]\|\|[[image:1574097391041-627.png]]		\|'''Telea'''\|\|[[image:1574097431794-254.png\|border]]\|\|[[image:1574097438229-534.png\|border]]
			\|-
			\|'''NavierStokes'''\|\|[[image:1574097384241-326.png\|border]]\|\|[[image:1574097391041-627.png\|border]]
	\|}		\|}


	~~For~~ our example, "Fill" worked just fine. ~~However,~~ "Inpaint" ~~might be necessary~~ to match the removed area to a more complicated background.		Keep in mind for our example, "Fill" worked just fine. "Inpaint" is more suited to match the removed area to a more complicated background than just white.

	</tab>		</tab>
Line 361:		Line 367:
	Refer to below for differences on the various dilation factors within "Shape Removal"		Refer to below for differences on the various dilation factors within "Shape Removal"

	{\|style="margin:auto"		{\|style="margin:auto" cellpadding="10" cellspacing="5"
	\|colspan="2" style="text-align:center"\|'''Dilation Factor (during Shape Detection)'''		\|colspan="2" style="text-align:center"\|'''Dilation Factor (during Shape Detection)'''
	\|-		\|-valign="top"
	\|[[image:1574101420230-605.png\|center]]\|\|This applies dilation to a sample image in order to aid the shape detection portion of the operation. This property is found in the "Preprocessing" section of the "Detection Settings" property window. If applied, it can make for a kind of "fuzzy" image matching. This can help match images on documents that don't exactly match the given sample image. However, it can produce false-positive matches as well.		\|[[image:1574101420230-605.png\|center\|318px]]\|\|This applies dilation to a sample image in order to aid the shape detection portion of the operation. This property is found in the "Preprocessing" section of the "Detection Settings" property window. If applied, it can make for a kind of "fuzzy" image matching. This can help match images on documents that don't exactly match the given sample image. However, it can produce false-positive matches as well.
	\|}		\|}


	{\|style="margin:auto"		{\|style="margin:auto" cellpadding="10" cellspacing="5"
	\|colspan="2" style="text-align:center"\|'''Dilation Factor (of the Shape Mask)'''		\|colspan="2" style="text-align:center"\|'''Dilation Factor (of the Shape Mask)'''
	\|-		\|-valign="top"
	\|[[image:1574102424838-119.png\|center]]\|\|This applies dilation to the Shape Mask. It is one of the main properties in the Shape Detection property panel. This will increase the size of the Dropout Mask. If a dilated Shape Mask overlays pixels from the binarized document that an un-dilated one would not, those pixels would be included in the Dropout Mask.		\|[[image:1574102424838-119.png\|center]]\|\|This applies dilation to the Shape Mask. It is one of the main properties in the Shape Detection property panel. This will increase the size of the Dropout Mask. If a dilated Shape Mask overlays pixels from the binarized document that an un-dilated one would not, those pixels would be included in the Dropout Mask.
	\|}		\|}


	{\|style="margin:auto"		{\|style="margin:auto" cellpadding="10" cellspacing="5"
	\|colspan="2" style="text-align:center"\|'''Mask Dilation Factor'''		\|colspan="2" style="text-align:center"\|'''Mask Dilation Factor'''
			\|-valign="top"
	\|[[image:1574102452213-358.png\|center]]\|\|This applies dilation to the dropout portion of the operation. This is a sub-property of the "Dropout Method" property. After the Dropout Mask is created, and those pixels are removed, applying dilation here fills more pixels in around the removed area.		\|[[image:1574102452213-358.png\|center]]\|\|This applies dilation to the dropout portion of the operation. This is a sub-property of the "Dropout Method" property. After the Dropout Mask is created, and those pixels are removed, applying dilation here fills more pixels in around the removed area.
	\|}		\|}