Line Detection and Line Removal - Revision history

Dgreenwood: /* Use cases for Line Detection */

2025-08-08T19:01:32Z

Use cases for Line Detection

← Older revision		Revision as of 14:01, 8 August 2025
Line 18:		Line 18:
	=== Use cases for Line Detection ===		=== Use cases for Line Detection ===

	Grooper can use Line Detection to:		Grooper can use the [[Layout Data\|layout data]] generated by Line Detection to:
	* ~~Identify~~ table boundaries and grid structures ~~for data extraction~~.		* Assist the [[Tabular Layout]] and [[Grid Layout]] table extract methods in identifying table boundaries and grid structures.
	* ~~Locate underlines~~, ~~boxes~~, ~~or separators for form field alignment~~.		* Help [[Tab Marking]] break up a document's text structure, inserting tabs where vertical lines are present.
			* Assist [[Paragraph Marking]] in determining divisions between paragraphs.
			* Generate layout data for various other features that utilize line locations, such as extractors that snap results to nearby line locations with their "Line Snap Options".
	* Provide visual overlays for reviewing detected lines in diagnostics or the UI.		* Provide visual overlays for reviewing detected lines in diagnostics or the UI.
	* Generate layout data for downstream processing, such as table extraction or snapping results to nearby lines with an extractor's "Line Snap Options".

	=== General configuration steps ===		=== General configuration steps ===

Dgreenwood at 20:24, 7 August 2025

2025-08-07T20:24:53Z

← Older revision		Revision as of 15:24, 7 August 2025
Line 1:		Line 1:
	'''Line Detection''' and '''Line Removal''' are two closely related IP Commands in Grooper. Both are designed to identify horizontal and vertical lines in document images, such as those found in forms, tables, or pre-printed backgrounds. Both commands generate layout data describing the position and orientation of detected lines, which can be used for downstream processing. However, while Line Detection only detects and analyzes lines, Line Removal will also remove lines from the image, cleaning up visual noise that may interfere with OCR or data extraction.		'''Line Detection''' and '''Line Removal''' are two closely related IP Commands in Grooper. Both are designed to identify horizontal and vertical lines in document images, such as those found in forms, tables, or pre-printed backgrounds. Both commands generate [[Layout Data\|layout data]] describing the position and orientation of detected lines, which can be used for downstream processing. However, while Line Detection only detects and analyzes lines, Line Removal will also remove lines from the image, cleaning up visual noise that may interfere with OCR or data extraction.

	== What is Line Detection? ==		== What is Line Detection? ==

Dgreenwood: /* General configuration steps */

2025-08-07T20:24:23Z

General configuration steps

← Older revision		Revision as of 15:24, 7 August 2025
Line 41:		Line 41:
	#** Advanced Line Detection		#** Advanced Line Detection
	#** Dash Detection		#** Dash Detection
	~~#** Maximum Speck Size~~
	#* The default settings work well for most scenarios. Check out the [[#About Line Detection settings\|About Line Detection settings]] section for more information on each of these properties.		#* The default settings work well for most scenarios. Check out the [[#About Line Detection settings\|About Line Detection settings]] section for more information on each of these properties.
	# Adjust "Comb Removal" settings as needed.		# Adjust "Comb Removal" settings as needed.
Line 51:		Line 50:
	#** Quiet Zone Size		#** Quiet Zone Size
	#** Minimum Weight		#** Minimum Weight
			#** Maximum Speck Size
	#* The default settings work well for most scenarios. Check out the [[#About Line Detection settings\|About Line Detection settings]] section for more information on each of these properties.		#* The default settings work well for most scenarios. Check out the [[#About Line Detection settings\|About Line Detection settings]] section for more information on each of these properties.
	# Adjust "Image Preprocessing" settings as needed.		# Adjust "Image Preprocessing" settings as needed.

Dgreenwood: /* General configuration steps */

2025-08-07T20:23:55Z

General configuration steps

← Older revision		Revision as of 15:23, 7 August 2025
Line 107:		Line 107:
	#** Advanced Line Detection		#** Advanced Line Detection
	#** Dash Detection		#** Dash Detection
	~~#** Maximum Speck Size~~
	#* The default settings work well for most scenarios. Check out the [[#About Line Detection settings\|About Line Detection settings]] section for more information on each of these properties.		#* The default settings work well for most scenarios. Check out the [[#About Line Detection settings\|About Line Detection settings]] section for more information on each of these properties.
	# Adjust "Comb Removal" settings as needed.		# Adjust "Comb Removal" settings as needed.
Line 117:		Line 116:
	#** Quiet Zone Size		#** Quiet Zone Size
	#** Minimum Weight		#** Minimum Weight
			#** Maximum Speck Size
	#* The default settings work well for most scenarios. Check out the [[#About Line Detection settings\|About Line Detection settings]] section for more information on each of these properties.		#* The default settings work well for most scenarios. Check out the [[#About Line Detection settings\|About Line Detection settings]] section for more information on each of these properties.
	# Adjust "Image Preprocessing" settings as needed.		# Adjust "Image Preprocessing" settings as needed.

Dgreenwood: /* Detection properties */

2025-08-07T20:23:26Z

Detection properties

← Older revision		Revision as of 15:23, 7 August 2025
Line 170:		Line 170:
	Below is a detailed explanation of each property, including its purpose, usage, and configuration guidance. Only the properties that both Line Detection and Line Removal share are documented here.		Below is a detailed explanation of each property, including its purpose, usage, and configuration guidance. Only the properties that both Line Detection and Line Removal share are documented here.

	=== Detection properties ===		=== Detection Settings properties ===

	; '''Minimum Line Length'''		; '''Minimum Line Length'''

Dgreenwood: /* When are IP Profiles executed? */

2025-08-07T20:23:00Z

When are IP Profiles executed?

Show changes

Dgreenwood: /* About Line Detection settings */

2025-08-07T20:15:38Z

About Line Detection settings

@@ Line 133: / Line 133: @@
 #* Fine-tune the Line Removal settings as needed.
 # The Line Removal step will execute as part of the IP Profile's execution flow.
 == Similarities and differences between Line Detection and Line Removal ==

Dgreenwood: /* General configuration steps */

2025-08-07T20:15:06Z

General configuration steps

@@ Line 96: / Line 96: @@
 # Right-click an [[IP Profile]] or [[IP Group]] to add a Line Removal [[IP Step]].
 # Select "Add Command" then "Feature Removal" then "Line Removal".
-# Configure detection properties as you would for Line Detection.
+# Adjust detection settings as needed.
-# Adjust the "Dropout Method" property to control how masked regions are filled (e.g., white fill, background fill, or interpolation).
+#* The detection settings are:
-# Set the "Trim Distance" property to control how much area around lines is also removed.
+#** Minimum Line Length
 # Test the IP Step/IP Group/IP Profile using the "Tester" tab. Use the Diagnostics panel's images and files to visualize results.
 #* Review the "Binarized", "Preprocessed", "Dropout Mask", and "Output Image" diagnostics to ensure lines are being removed as intended.

Dgreenwood: /* Summary Table */

2025-08-07T20:05:08Z

Summary Table

← Older revision		Revision as of 15:05, 7 August 2025
Line 196:		Line 196:
	\| '''Comb Removal''' \|\| Remove combs (short stubs) \|\| Clean up comb boxes/grids		\| '''Comb Removal''' \|\| Remove combs (short stubs) \|\| Clean up comb boxes/grids
	\|-		\|-
	\| '''Minimum Length (Comb)''' \|\| Shortest comb length \|\| Target checkboxes/stubs		\| '''Minimum Length (Comb Removal)''' \|\| Shortest comb length \|\| Target checkboxes/stubs
	\|-		\|-
	\| '''Minimum Fill (Comb)''' \|\| Fill for combs \|\| Reduce false positives		\| '''Minimum Fill (Comb Removal)''' \|\| Fill for combs \|\| Reduce false positives
	\|-		\|-
	\| '''Quiet Zone Size (Comb)''' \|\| Whitespace around combs \|\| Avoid misclassifying text		\| '''Quiet Zone Size (Comb Removal)''' \|\| Whitespace around combs \|\| Avoid misclassifying text
	\|-		\|-
	\| '''Minimum Weight (Comb)''' \|\| Quiet zone fill \|\| Stricter comb separation		\| '''Minimum Weight (Comb Removal)''' \|\| Quiet zone fill \|\| Stricter comb separation
	\|-		\|-
	\| '''Maximum Speck Size''' \|\| Remove small artifacts \|\| Clean up noise		\| '''Maximum Speck Size''' \|\| Remove small artifacts \|\| Clean up noise
	\|-		\|-
	\| '''Binarization Settings''' \|\| Convert to black/white \|\| Optimize detection		\| '''Binarization Settings (Image Preprocessing)''' \|\| Convert to black/white \|\| Optimize detection
	\|-		\|-
	\| '''Dropout Font Size''' \|\| Remove text before detection \|\| Prevent text/line confusion		\| '''Dropout Font Size (Image Prepressing)''' \|\| Remove text before detection \|\| Prevent text/line confusion
	\|}		\|}

Dgreenwood: /* Summary Table */

2025-08-07T20:04:15Z

Summary Table

← Older revision		Revision as of 15:04, 7 August 2025
Line 204:		Line 204:
	\| '''Minimum Weight (Comb)''' \|\| Quiet zone fill \|\| Stricter comb separation		\| '''Minimum Weight (Comb)''' \|\| Quiet zone fill \|\| Stricter comb separation
	\|-		\|-
	\| '''Maximum Speck Size ~~(Comb)~~''' \|\| Remove small artifacts \|\| Clean up noise		\| '''Maximum Speck Size''' \|\| Remove small artifacts \|\| Clean up noise
	\|-		\|-
	\| '''Binarization Settings''' \|\| Convert to black/white \|\| Optimize detection		\| '''Binarization Settings''' \|\| Convert to black/white \|\| Optimize detection