Skip to content

AbsoluteStaticCrop

Crop a Region of Interest (RoI) from an image, using absolute coordinates.

This is useful when placed after an ObjectDetection block as part of a multi-stage workflow. For example, you could use an ObjectDetection block to detect objects, then the AbsoluteStaticCrop block to crop objects, then an OCR block to run character recognition on each of the individual cropped regions.

Properties

Name Type Description Refs
name str The unique name of this step..
x_center int Center X of static crop (absolute coordinate).
y_center int Center Y of static crop (absolute coordinate).
width int Width of static crop (absolute value).
height int Height of static crop (absolute value).

The Refs column marks possibility to parametrise the property with dynamic values available in workflow runtime. See Bindings for more info.

Available Connections

Check what blocks you can connect to AbsoluteStaticCrop.

The available connections depend on its binding kinds. Check what binding kinds AbsoluteStaticCrop has.

Bindings
  • input

    • images (Batch[image]): The image to infer on.
    • x_center (integer): Center X of static crop (absolute coordinate).
    • y_center (integer): Center Y of static crop (absolute coordinate).
    • width (integer): Width of static crop (absolute value).
    • height (integer): Height of static crop (absolute value).
  • output

Example JSON definition of AbsoluteStaticCrop step
{
    "name": "<your_step_name_here>",
    "type": "AbsoluteStaticCrop",
    "images": "$inputs.image",
    "x_center": 40,
    "y_center": 40,
    "width": 40,
    "height": 40
}