# Detection Offset

### 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

<figure><img src="/files/MiO0HY6DvmLv2HZyRazo" alt=""><figcaption><p>The Detection Offset block.</p></figcaption></figure>

### 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:

<figure><img src="/files/OtqTGm5lh0gWSzOZvTlj" alt=""><figcaption><p>The defect in the image is magnified.</p></figcaption></figure>

For reference, here is the input image:

<figure><img src="/files/yXDkFembyzdowye7MyED" alt=""><figcaption></figcaption></figure>

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.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.roboflow.com/workflows/workflow-blocks/transformations/detection-offset.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.