Negative Region Removal

Sets the smallest allowable width or height for a region to be considered as a negated area. This helps filter out small marks, specks, or noise that do not represent meaningful negated regions. The value can be specified in display units such as pt, in, or px.

• Increase this value to ignore small, irrelevant regions.
• Decrease to detect smaller negated areas, such as small field labels.

Review the Dark Areas diagnostic image to verify that all intended negated regions are detected. If some regions are missing, reduce the value; if too many small regions are detected, increase it.

Controls the minimum area (width × height) required for a region to be considered as a negated area. This helps filter out small, non-informative regions. Specify the value in squared display units (e.g., 18pt means an area equal to or greater than an 18pt × 18pt square).

• Increase to ignore small regions and focus on larger, more significant negated areas.
• Decrease to allow detection of smaller negated regions.

Use the Dark Areas diagnostic image to tune this property. If important regions are not detected, lower the value.

Determines how much of the border or outline of a negated region is preserved after processing.

• A positive value leaves an outline of the specified thickness around the region.
• A value of zero removes the region without leaving an outline.
• A negative value removes the region and cleans the edges to the specified distance.

Example:

Adjust this property to control whether an outline is left, and how thick it should be. For most OCR scenarios, a value of zero or a small positive value is recommended.

The 'Binarization Settings' property determines how the input image is converted to black and white for negated region detection. Proper binarization is critical for accurate detection of dark and light regions.

• Use the Binarized diagnostic image to verify that negated regions are clearly visible and separated from the background.
• Adjust thresholding and method (e.g., Auto, Adaptive) to suit your document type and image quality.

If negated regions are not detected or are merged with the background, try a different binarization method or adjust the threshold.

Edge repair fills gaps along the edges of negated regions and separates characters that touch the outside edge of a negated region. This is especially useful for noisy or low-quality scans where text may bleed into the background.

• Enable for degraded or complex documents to improve region detection.
• Disable for clean, high-resolution documents to improve performance.

Use the Clean Image diagnostic to see the effect of edge repair.

Controls how aggressively small white blobs (such as specks or characters) inside negated regions are filled before region detection. Specify the value in display units (e.g., 14pt means an area equal to a 14pt × 14pt square).

• Increase to fill larger whitespace areas, making regions more solid.
• Decrease to preserve small holes or gaps inside negated regions.

Use the Filled diagnostic image to tune this property. The goal is to produce solid black regions for each negated area.

The 'Trim Factor' property controls the erosion of high-frequency features (such as lines and characters) to isolate solid black regions representing negated areas. Higher values erode more features, while lower values preserve more detail.

• Increase to remove more noise and connect fragmented regions.
• Decrease to preserve fine details or when regions are being over-eroded.

Use the Candidates diagnostic image to tune this property. The objective is to produce a candidates image where each negated region is a solid black area, and connecting lines have been eroded away.

The 'Command Type Name' property shows the user-friendly name of the IP Command as it appears in the Grooper UI. This helps users identify which command is being configured or executed, especially when working with IP Profiles containing multiple commands.

This property is read-only and is automatically set based on the command's type.

The 'Supported Pixel Formats' property lists the image pixel formats that the IP Command can process. If an image does not match one of these formats, the command will be skipped for that image.

• By default, all pixel formats are supported unless a derived command restricts this list.
• Example formats include Pixel8bppGrayscale, Pixel24bppBgr, and Pixel1bppIndexed.

Use this property to verify compatibility when building IP Profiles or troubleshooting why a command did not execute.