Detection Offset

Add padding around detected regions.

About this block

The Detection Offset block lets you add a padding around regions detected by an object detection model or segmentation model.

This block is useful if you want to add space around a detection. You may want to do this if you want to see some background around the detected regions in an image.

This block works with:

• Object detection models

• Segmentation models

The Detection Offset block.

What you can send into this block

To use this block, you need:

1. An input image, video frame, or a cropped region in your image, and;

2. Predictions from an Object Detection or Segmentation model.

What this block returns

The Detection Offset block returns a version of the xyxy coordinates returned by a detection model. These coordinates have padding (space).

These coordinates can then be passed into any block that supports detections (i.e. an OCR Model, or a Bounding Box Visualization).

Here is an example showing raw detections displayed with a Bounding Box Visualization (left) and detections to which an offset (padding) has been applied:

The defect in the image is magnified.

For reference, here is the input image:

In the result from the block, the detected region is made bigger.

Use cases

This block is useful if you want to see the results from a model on an image. This is common during testing.

Because visualizing predictions adds a small amount of overhead to running a Workflow, we only recommend adding a Visualization in production if you need to see the location of results from your model.