<!--
{
  "availability" : [
    "iOS: 14.0.0 -",
    "iPadOS: 14.0.0 -"
  ],
  "documentType" : "symbol",
  "framework" : "ARKit",
  "identifier" : "/documentation/ARKit/ARSkeleton/JointName/init(_:)",
  "metadataVersion" : "0.1.0",
  "role" : "Initializer",
  "symbol" : {
    "kind" : "Initializer",
    "modules" : [
      "ARKit"
    ],
    "preciseIdentifier" : "c:@F@ARSkeletonJointNameForRecognizedPointKey"
  },
  "title" : "init(_:)"
}
-->

# init(_:)

Returns a joint name that corresponds to a key point defined in a human body pose.

```
init?(_ recognizedPointKey: VNRecognizedPointKey)
```

## Parameters

`recognizedPointKey`

The argument key point.

## Discussion

This function matches human body key points defined by the Vision framework with joint names defined by ARKit. This function may return `nil` if the key point doesn’t map to a joint name. For more information about key points, see <doc://com.apple.documentation/documentation/Vision/detecting-human-body-poses-in-images>.

---

Copyright &copy; 2026 Apple Inc. All rights reserved. | [Terms of Use](https://www.apple.com/legal/internet-services/terms/site.html) | [Privacy Policy](https://www.apple.com/privacy/privacy-policy)