image-masker-by-region — Masking AI Model

Details

• CategoryMasking
• Year-1
• License

Inputs & Outputs

ImageInput · image

Sets the mask size; its pixels are not read

RegionsInput · string

One region per line: 'x1,y1,x2,y2,...' polygons or 'xmin,ymin,xmax,ymax' boxes

ImageOutput · image

Black and white mask, white where the regions are

Parameters

use_bounding_boxboolean · default false

Read the regions as bounding boxes instead of polygons

When false (default), a line of 3 or more points is filled as the polygon it describes. When true, it is filled as its axis-aligned bounding box instead. A 4-value 'xmin,ymin,xmax,ymax' line is a rectangle either way.

Tags

• mask-creation
• polygon
• bounding-box
• coordinate-based
• ocr

Alternatives in Image Masking

• Image Masker by Class

  Build a B&W mask from segmentation/detection by class name.

• Image Masker by Coord

  Build a B&W mask from explicit bbox coordinates.

• Manuel Image Masker

  Hand-draw a B&W mask with brush tools.

• Mask Grow / Shrink

  Grow or shrink a mask by N pixels. Instant.

• Object Picker

  Interactive — click segmented objects to build a mask.