<!--
{
  "availability" : [

  ],
  "documentType" : "symbol",
  "framework" : "Vision",
  "identifier" : "/documentation/Vision",
  "metadataVersion" : "0.1.0",
  "role" : "Framework",
  "symbol" : {
    "kind" : "Framework",
    "modules" : [
      "Vision"
    ],
    "preciseIdentifier" : "Vision"
  },
  "title" : "Vision"
}
-->

# Vision

Analyze image and video content in your app using computer vision algorithms for object detection, text recognition, and image segmentation.

## Overview

The Vision framework provides pretrained machine learning models for computer vision tasks. Use Vision to analyze still images and video for a variety of purposes, including:

- Recognizing text in 26 languages across everyday objects, documents, and photos
- Detecting barcodes and QR codes
- Detecting faces and analyzing facial features
- Isolating people and foreground objects with subject lifting
- Tracking body poses of people and animals for action and gesture recognition
- Classifying images for categorization and search
- Measuring image quality and comparing visual similarity

![A dog isolated from its background through subject lifting.](images/Vision/vision-framework-subject-lifting@2x.png)

All Vision analysis tasks follow the same steps: create a request, perform it on an image or video frame, and read the resulting observations.
For example, to detect text in an image, you create a request for the type of analysis you want to perform. Each request conforms to the [`VisionRequest`](/documentation/Vision/VisionRequest) protocol.

```swift
let request = RecognizeTextRequest()
let observations = try await request.perform(on: imageData)

// Store observations for use in your app
var scannedText: [String] = []

for observation in observations {
    scannedText.append(observation.transcript)
}
```

The request returns an array of observation objects that contain the image-analysis results. Each observation type provides specific details about the analysis results, such as recognized text, confidence scores, and bounding box locations.

For observations that describe image locations -—- such as face bounding boxes or text regions -—- Vision uses a normalized coordinate system where values range from `0.0` to `1.0`, with the origin at the lower-left corner. For more information on coordinate types and conversion helpers, see [Image locations and regions](https://developer.apple.com/documentation/vision#Image-locations-and-regions).

You can also perform multiple requests on the same image, for more information see [`ImageRequestHandler`](/documentation/Vision/ImageRequestHandler) in the Request handlers section.

This pattern applies to all Vision requests, whether you’re detecting faces, tracking motion, analyzing image quality, or performing custom analysis with Core ML models. Each request type returns observations specific to its analysis task.

> Note:
> Starting in iOS 18.0, the Vision framework provides a new Swift-only API. See <doc://Vision/documentation/Vision/original-objective-c-and-swift-api> to view the original API.

## Topics

### Text and document analysis

[Locating and displaying recognized text](/documentation/Vision/locating-and-displaying-recognized-text)

Perform text recognition on a photo using the Vision framework’s text-recognition request.

[Recognizing tables within a document](/documentation/Vision/recognize-tables-within-a-document)

Scan a document that contains a table and extract its content in a formatted way.

[`struct DetectBarcodesRequest`](/documentation/Vision/DetectBarcodesRequest)

A request that detects barcodes in an image.

[`struct DetectDocumentSegmentationRequest`](/documentation/Vision/DetectDocumentSegmentationRequest)

A request that detects rectangular regions that contain text in the input image.

[`struct DetectTextRectanglesRequest`](/documentation/Vision/DetectTextRectanglesRequest)

An image-analysis request that finds regions of visible text in an image.

[`struct RecognizeDocumentsRequest`](/documentation/Vision/RecognizeDocumentsRequest)

An image-analysis request to scan an image of a document and provide information about its structure.

[`struct RecognizeTextRequest`](/documentation/Vision/RecognizeTextRequest)

An image-analysis request that recognizes text in an image.

### Facial analysis

[Analyzing a selfie and visualizing its content](/documentation/Vision/analyzing-a-selfie-and-visualizing-its-content)

Calculate face-capture quality and visualize facial features for a collection of images using the Vision framework.

[`struct DetectFaceCaptureQualityRequest`](/documentation/Vision/DetectFaceCaptureQualityRequest)

A request that produces a floating-point number that represents the capture quality of a face in a photo.

[`struct DetectFaceLandmarksRequest`](/documentation/Vision/DetectFaceLandmarksRequest)

An image analysis request that finds facial features like eyes and mouth in an image.

[`struct DetectFaceRectanglesRequest`](/documentation/Vision/DetectFaceRectanglesRequest)

A request that finds faces within an image.

### Image segmentation and subject lifting

[Isolating an object from a tap, box, or scribble](/documentation/Vision/segmenting-objects-with-iterative-refinement)

Generate and refine a mask that isolates an object in an image based on a person’s selection.

[Segmenting objects using taps, scribbles or rectangles](/documentation/Vision/segmenting-objects-using-taps-scribbles-or-rectangles)

Select objects or regions in a photo using taps, scribbles, or rectangle selection, and generate a segmentation mask using the iterative segmentation API.

[`struct GenerateForegroundInstanceMaskRequest`](/documentation/Vision/GenerateForegroundInstanceMaskRequest)

A request that generates an instance mask of noticeable objects to separate from the background.

[`struct GeneratePersonInstanceMaskRequest`](/documentation/Vision/GeneratePersonInstanceMaskRequest)

A request that produces a mask of individual people it finds in the input image.

[`class GeneratePersonSegmentationRequest`](/documentation/Vision/GeneratePersonSegmentationRequest)

A request that produces a matte image for a person it finds in the input image.

[`class GenerateIterativeSegmentationRequest`](/documentation/Vision/GenerateIterativeSegmentationRequest)

A request that generates a segmentation mask from points, a rectangle, or a scribble.

### Pose analysis

[`struct DetectAnimalBodyPoseRequest`](/documentation/Vision/DetectAnimalBodyPoseRequest)

A request that detects an animal body pose.

[`class DetectHumanBodyPose3DRequest`](/documentation/Vision/DetectHumanBodyPose3DRequest)

A request that detects points on human bodies in 3D space, relative to the camera.

[`struct DetectHumanBodyPoseRequest`](/documentation/Vision/DetectHumanBodyPoseRequest)

A request that detects a human body pose.

[`struct DetectHumanHandPoseRequest`](/documentation/Vision/DetectHumanHandPoseRequest)

A request that detects a human hand pose.

[Supporting Pose Types](/documentation/Vision/supporting-pose-types)

Types you use when working with pose analysis.

### Image classification and recognition

[Classifying images for categorization and search](/documentation/Vision/classifying-images-for-categorization-and-search)

Analyze and label images using a Vision classification request.

[`struct ClassifyImageRequest`](/documentation/Vision/ClassifyImageRequest)

A request to classify an image.

[`struct DetectHumanRectanglesRequest`](/documentation/Vision/DetectHumanRectanglesRequest)

A request that finds rectangular regions that contain people in an image.

[`struct RecognizeAnimalsRequest`](/documentation/Vision/RecognizeAnimalsRequest)

A request that recognizes animals in an image.

### Shape and edge detection

[`struct DetectContoursRequest`](/documentation/Vision/DetectContoursRequest)

A request that detects the contours of the edges of an image.

[`struct DetectHorizonRequest`](/documentation/Vision/DetectHorizonRequest)

An image-analysis request that determines the horizon angle in an image.

[`struct DetectRectanglesRequest`](/documentation/Vision/DetectRectanglesRequest)

An image-analysis request that finds projected rectangular regions in an image.

### Image quality and saliency analysis

[Implementing saliency-based image cropping in iOS and watchOS](/documentation/Vision/implementing-saliency-based-image-cropping-in-iOS-and-watchOS)

Crop regions most likely drawing people’s attention from an image in your iOS or watchOS app.

[Generating high-quality thumbnails from videos](/documentation/Vision/generating-thumbnails-from-videos)

Identify the most visually pleasing frames in a video by using the image-aesthetics scores request.

[`struct CalculateImageAestheticsScoresRequest`](/documentation/Vision/CalculateImageAestheticsScoresRequest)

A request that analyzes an image for aesthetically pleasing attributes.

[`struct DetectLensSmudgeRequest`](/documentation/Vision/DetectLensSmudgeRequest)

A request that detects a smudge on a lens from an image or video frame capture.

[`struct GenerateAttentionBasedSaliencyImageRequest`](/documentation/Vision/GenerateAttentionBasedSaliencyImageRequest)

An object that produces a heat map that identifies the parts of an image most likely to draw attention.

[`struct GenerateObjectnessBasedSaliencyImageRequest`](/documentation/Vision/GenerateObjectnessBasedSaliencyImageRequest)

A request that generates a heat map that identifies the parts of an image most likely to represent objects.

### Motion and object tracking

[`class DetectTrajectoriesRequest`](/documentation/Vision/DetectTrajectoriesRequest)

A request that detects the trajectories of shapes moving along a parabolic path.

[`class TrackObjectRequest`](/documentation/Vision/TrackObjectRequest)

An image analysis request that tracks the movement of a previously identified object across multiple images or video frames.

[`class TrackOpticalFlowRequest`](/documentation/Vision/TrackOpticalFlowRequest)

A request that determines the direction change of vectors for each pixel from a previous to current image.

[`class TrackRectangleRequest`](/documentation/Vision/TrackRectangleRequest)

An image-analysis request that tracks movement of a previously identified rectangular object across multiple images or video frames.

### Image registration and comparison

[`struct GenerateImageFeaturePrintRequest`](/documentation/Vision/GenerateImageFeaturePrintRequest)

An image-based request to generate feature prints from an image.

[`class TrackHomographicImageRegistrationRequest`](/documentation/Vision/TrackHomographicImageRegistrationRequest)

An image-analysis request that you track over time to determine the perspective warp matrix necessary to align the content of two images.

[`class TrackTranslationalImageRegistrationRequest`](/documentation/Vision/TrackTranslationalImageRegistrationRequest)

An image-analysis request that you track over time to determine the affine transform necessary to align the content of two images.

### Custom Core ML integration

[`struct CoreMLRequest`](/documentation/Vision/CoreMLRequest)

An image-analysis request that uses a Core ML model to process images.

### Foundation Models integration

[`struct BarcodeReaderTool`](/documentation/Vision/BarcodeReaderTool)

A tool that scans machine-readable codes in an image.

[`struct OCRTool`](/documentation/Vision/OCRTool)

A tool that recognizes text in an image.

### Protocols

[`protocol ImageProcessingRequest`](/documentation/Vision/ImageProcessingRequest)

A type for image-analysis requests that focus on a specific part of an image.

[`protocol PoseProviding`](/documentation/Vision/PoseProviding)

An observation that provides a collection of joints that make up a pose.

[`protocol StatefulRequest`](/documentation/Vision/StatefulRequest)

The protocol for a type that builds evidence of a condition over time.

[`protocol TargetedRequest`](/documentation/Vision/TargetedRequest)

A type for analyzing two images together.

[`protocol VisionObservation`](/documentation/Vision/VisionObservation)

A type for objects produced by image-analysis requests.

[`protocol VisionRequest`](/documentation/Vision/VisionRequest)

A type for image-analysis requests.

[`protocol DownloadableAssetsRequest`](/documentation/Vision/DownloadableAssetsRequest)

A request whose execution depends on assets that may need to be downloaded.

[`enum DownloadableAssetsRequestStatus`](/documentation/Vision/DownloadableAssetsRequestStatus)

The status of the assets required by a [`DownloadableAssetsRequest`](/documentation/Vision/DownloadableAssetsRequest).

### Request handlers

[`class ImageRequestHandler`](/documentation/Vision/ImageRequestHandler)

An object that processes one or more image-analysis requests pertaining to a single image.

[`class TargetedImageRequestHandler`](/documentation/Vision/TargetedImageRequestHandler)

An object that performs image-analysis requests on two images.

[`class VideoProcessor`](/documentation/Vision/VideoProcessor)

An object that performs offline analysis of video content.

### Image locations and regions

[`struct NormalizedPoint`](/documentation/Vision/NormalizedPoint)

A point in a 2D coordinate system.

[`struct NormalizedRect`](/documentation/Vision/NormalizedRect)

The location and dimensions of a rectangle.

[`typealias NormalizedRegion`](/documentation/Vision/NormalizedRegion)

A polygon composed of normalized points.

[`struct NormalizedCircle`](/documentation/Vision/NormalizedCircle)

The center point and radius of a 2D circle.

[`protocol BoundingBoxProviding`](/documentation/Vision/BoundingBoxProviding)

A protocol for objects that have a bounding box.

[`protocol BoundingRegionProviding`](/documentation/Vision/BoundingRegionProviding)

A protocol for objects that have a defined boundary in an image.

[`protocol QuadrilateralProviding`](/documentation/Vision/QuadrilateralProviding)

A protocol for objects that have a bounding quadrilateral.

[`enum CoordinateOrigin`](/documentation/Vision/CoordinateOrigin)

The origin of a coordinate system relative to an image.

### Errors

[`enum VisionError`](/documentation/Vision/VisionError)

The errors that the framework produces.

### Legacy API

[Original Objective-C and Swift API](/documentation/Vision/original-objective-c-and-swift-api)


---

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)