# Classification

{% hint style="info" %}
Automated Classification routines are an advanced feature that require a SpatialExplorer Pro license. Refer to [Licensing](/spatialexplorer/installation/licensing-1.md) for more information.
{% endhint %}

To filter or classify a .cloud file, make sure a .cloud file has been created and is loaded. Refer to the [Create a Point Cloud](/spatialexplorer/work-offline/workflow/create-a-cloud.md) section.

Once a .cloud file has been created, click the name of the created .cloud file underneath "Pointclouds" in the Project tree window. In this example, the created point cloud is "20180601-214257".

![](/files/-LtCd1P7UgH7CRP3egVD)

In the submenu, select the Edit tab and click on the funnel icon to access the filtering menu.

![Filter point cloud icon](/files/-M05GQwWzc1icSAyDPh_)

 There are automated and customizable classification routines including ground isolation and noise removal. Points can also be classified interactively using user-defined selections. Refer to [Selections](/spatialexplorer/work-offline/workflow/create-a-cloud/make-selections.md) for more details. Once points have been classified, the user can hide or show selected classes using the [Visibility](https://phoenixlidar.gitbook.io/documentation/software-overview/spatial-explorer/spatialexplorer-user-interface/project#visibility) tools. When you export your cloud to LAS, you can also choose to omit certain classes. 

## Filtering Routines

There are three options by which to filter a .cloud file: Assign Class, Find Noise, and Find Ground.

### Assign Class

![](/files/-M0tHl5GwIX63R-wsGfl)

To assign a class to points, choose the classes you'd like to input into the filter. Then select the output class that you'd like to assign them to. Click the "Run Filter" radio button to begin the filtering the pointcloud.

It is also possible to use the selection tools to make interactive classifications. Refer to [Make Selections](/spatialexplorer/work-offline/workflow/create-a-cloud/make-selections.md) for more information. Once a selection in the cloud has been made, you can assign a class to those points. 

### Find Noise

![](/files/-M0tIoQ5MLEaIyC1dMzK)

The noise filter assigns the output class to all points that have less than X points in their neighborhood radius of Y meters. Neighboring classes can be specified as well. Before running the filter, ensure that the desired output class is chosen.

### Find Ground

![](/files/-M0xGVOAc9v8rW484_0Y)

The ground filter classifies points based on the inputted parameters. Disable input classes that should not be considered as ground such as any noise classes that were previously determined.

{% hint style="info" %}
Ensure that you "Save Classification To Cloud" before exporting to LAS
{% endhint %}


---

# 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-6.phoenixlidar.com/spatialexplorer/work-offline/workflow/create-a-cloud/filtering.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.