Hole Punch Removal

A combination of the following flags:

The 'Edges' property specifies which sides of the image (top, bottom, left, right, or all) will be analyzed for hole punch artifacts.

• Select one or more edges to match the expected location of hole punches in your documents.
• Only blobs detected within the allowed zones along these edges will be considered for removal.

Example

To remove hole punches from the left and top edges only, select "Left" and "Top".

The 'Size Range' property defines the minimum and maximum diameter (in display units) for blobs to be considered hole punches.

• Specify the range using units such as mm, in, or px.
• Only blobs whose width and height fall within this range will be considered.
• Use standard hole punch sizes as a reference (e.g., 5mm to 10mm).

Example

To match standard US 3-hole punches, set the range to 5mm - 10mm.

The 'Maximum Inset' property sets how far from the specified edge a blob can be and still be considered a hole punch.

• Blobs further from the edge than this value are excluded from consideration.
• Specify the value in units such as mm, in, or px.

Example

Set this property to 25mm to allow detection of hole punches up to 25mm from the edge.

The 'Trim Factor' property controls the amount of erosion applied to the image to remove high-frequency features (such as lines and characters) and isolate solid black regions.

• Higher values erode away more features, making it easier to isolate hole punches.
• Lower values preserve more features, which may be necessary for faint or small hole punches.
• Review the "Candidates" diagnostic image to tune this property.

Example

Increase this value if non-hole punch features are being detected; decrease if hole punches are not being detected.

The 'Max Square Deviation' property sets the maximum allowed difference between the width and height of a blob for it to be considered a hole punch.

• Lower values require blobs to be more perfectly square (and thus more likely to be circular).
• Higher values allow more elliptical shapes to be considered.
• This helps prevent ellipses or elongated blobs from being mistaken for hole punches.

Example

Set this property to 0.1 (10%) to allow only nearly circular blobs.

The 'Min Circle Similarity' property sets the minimum required similarity between a blob and a perfect circle.

• Values range from 0 (no similarity) to 1 (perfect match).
• Increase this value to require blobs to be more circular.
• Review the diagnostic log for similarity scores when tuning this property.

Example

Set this property to 0.9 to require blobs to be at least 90% similar to a perfect circle.

Can be one of the following types:

The 'Dropout Method' property determines the technique used to remove or replace regions of the image identified by the feature mask. This allows you to control the visual result of the dropout operation, depending on your processing goals.

Common dropout methods include:

• Filling masked regions with a solid color (such as white or the detected background color).
• Replacing masked regions with interpolated content from surrounding pixels.
• Applying custom fill logic as defined by the selected Dropout Method.

Choosing the appropriate dropout method is important for maintaining the readability and appearance of the processed image. For example, filling with white may be suitable for removing background noise, while interpolation may be preferred when removing lines or halftones from text regions.

Example: To remove halftone patterns and fill the resulting regions with the detected background color, select the 'Background Fill' option from the 'Dropout Method' dropdown.

Review the diagnostic images generated in diagnostic mode to verify that the selected method produces the desired effect on your sample images.

The 'Smoothing Factor' property controls the amount of median filtering applied to the image to reduce noise and small artifacts.

• Higher values apply more smoothing, which can help with noisy or low-quality scans.
• Lower values preserve more detail, which may be necessary for faint or small hole punches.
• Typical values range from 1 to 3.

Example

Set this property to 2 for moderate smoothing, or 1 for minimal smoothing.

The 'Binarization Settings' property determines the thresholding method and parameters used to create the binarized image that serves as the basis for feature detection in Binary Dropout commands.

Binarization is a critical preprocessing step: it transforms the input image into an 8-bit black and white version, making features such as barcodes, halftones, or lines more distinct and easier to detect.

Configuration Guidance

• Select the thresholding method using the 'Method' property within 'Binarization Settings'.
• Adjust additional parameters such as threshold value, window size, kernel type, and adjustment as needed for your document type.
• For most standard documents, 'Auto' or 'Adaptive' methods provide the best results.
• For documents with variable backgrounds or lighting, use 'Adaptive' or 'Dynamic' and tune the window size and kernel type.

Notes

• The quality of the binarized image directly affects the accuracy of feature detection and dropout.
• Review the diagnostic output to ensure that the features you wish to remove are clearly visible in the binarized image.

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.