# Auto-detect with manual review

When using CameraSnap in the **Auto-detect with review** mode, **CameraSnap** finds matching features (generally referred to as keypoints), then displays these feature matches in the **CameraSnap** **Match Explorer**:

<figure><img src="/files/vn6WoCyn186QfAdeuVTX" alt=""><figcaption></figcaption></figure>

This allows the user to remove or add matches.  Matches shown in the table are a feature match between two images. The image numbers and receptor numbers associated with the match are displayed in the leftmost columns of the table. To manually add a match, so the [Manually-Created mode](/spatialexplorer-8-and-9/user-interface/toolbars/workflow/camera-snap/manually-created-matches.md) (the process is the same).

**Approach Distance** is one of the most useful fields in the Match Explorer. Approach Distance is calculated by projecting a ray from each image to the keypoint (or feature), and computing the difference in position of the rays. Generally, the smaller approach distance, the better the match.&#x20;

{% hint style="info" %}
You can sort the matches by clicking on the column headers. A quick and easy way to filter out bad matches is to sort by **Approach Distance**, then select and remove all matches with an approach distance greater than approximately **0.10 m**.&#x20;
{% endhint %}

Try to retain at least 20 matches, however ideally you have much more. Once you have filtered the matches, you can click **Calibrate** and CameraSnap will proceed with Calibration using the available feature matches. Review the [CameraSnap report](/spatialexplorer-8-and-9/user-interface/toolbars/workflow/camera-snap/camerasnap-reports.md) to ensure a proper calibration was achieved.&#x20;


---

# 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.phoenixlidar.com/spatialexplorer-8-and-9/user-interface/toolbars/workflow/camera-snap/auto-detect-with-manual-review.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.