let request = VNGenerateForegroundInstanceMaskRequest()
let handler = VNImageRequestHandler(cgImage: image)

try handler.perform([request])

guard let observation = request.results?.first as? VNInstanceMaskObservation else {
    return
}

let point = CGPoint(x: 0.5, y: 0.5)  // Center of image
let instance = observation.instanceAtPoint(point)

if instance == 0 {
    print("Background tapped")
} else {
    print("Instance \(instance) tapped")
}

// All instances, full resolution
let mask = try observation.createScaledMask(
    for: observation.allInstances,
    croppedToInstancesContent: false
)

// Single instance, cropped
let instances = IndexSet(integer: 1)
let croppedMask = try observation.createScaledMask(
    for: instances,
    croppedToInstancesContent: true
)

let instanceMask = observation.instanceMask

CVPixelBufferLockBaseAddress(instanceMask, .readOnly)
defer { CVPixelBufferUnlockBaseAddress(instanceMask, .readOnly) }

let baseAddress = CVPixelBufferGetBaseAddress(instanceMask)
let width = CVPixelBufferGetWidth(instanceMask)
let bytesPerRow = CVPixelBufferGetBytesPerRow(instanceMask)

// Convert normalized tap to pixel coordinates
let pixelPoint = VNImagePointForNormalizedPoint(
    CGPoint(x: normalizedX, y: normalizedY),
    width: imageWidth,
    height: imageHeight
)

// Calculate byte offset
let offset = Int(pixelPoint.y) * bytesPerRow + Int(pixelPoint.x)

// Read instance label
let label = UnsafeRawPointer(baseAddress!).load(
    fromByteOffset: offset,
    as: UInt8.self
)

let instances = label == 0 ? observation.allInstances : IndexSet(integer: Int(label))

let interaction = ImageAnalysisInteraction()
interaction.preferredInteractionTypes = .imageSubject  // Or .automatic
imageView.addInteraction(interaction)

let overlayView = ImageAnalysisOverlayView()
overlayView.preferredInteractionTypes = .imageSubject
nsView.addSubview(overlayView)

let analyzer = ImageAnalyzer()
let configuration = ImageAnalyzer.Configuration([.text, .visualLookUp])

let analysis = try await analyzer.analyze(image, configuration: configuration)

// Get all subjects
let subjects = analysis.subjects

// Look up subject at tap
if let subject = try await analysis.subject(at: tapPoint) {
    // Process subject
}

// Change highlight state
analysis.highlightedSubjects = Set([subjects[0], subjects[1]])

// Single subject image
let subjectImage = subject.image

// Composite multiple subjects
let compositeImage = try await analysis.image(for: [subject1, subject2])

let request = VNGeneratePersonSegmentationRequest()
// Configure quality level if needed
try handler.perform([request])

guard let observation = request.results?.first as? VNPixelBufferObservation else {
    return
}

let personMask = observation.pixelBuffer  // CVPixelBuffer

let request = VNGeneratePersonInstanceMaskRequest()
try handler.perform([request])

guard let observation = request.results?.first as? VNInstanceMaskObservation else {
    return
}

// Same InstanceMaskObservation API as foreground instance masks
let allPeople = observation.allInstances  // Up to 4 people (1-4)

// Get mask for person 1
let person1Mask = try observation.createScaledMask(
    for: IndexSet(integer: 1),
    croppedToInstancesContent: false
)

let request = VNDetectHumanHandPoseRequest()
request.maximumHandCount = 2  // Default: 2, increase if needed

let handler = VNImageRequestHandler(cgImage: image)
try handler.perform([request])

for observation in request.results as? [VNHumanHandPoseObservation] ?? [] {
    // Process each hand
}

// Get all points
let allPoints = try observation.recognizedPoints(.all)

// Get index finger points only
let indexPoints = try observation.recognizedPoints(.indexFinger)

// Get specific point
let thumbTip = try observation.recognizedPoint(.thumbTip)
let indexTip = try observation.recognizedPoint(.indexTip)

// Check confidence
guard thumbTip.confidence > 0.5 else { return }

// Access location (normalized coordinates, lower-left origin)
let location = thumbTip.location  // CGPoint

let thumbTip = try observation.recognizedPoint(.thumbTip)
let indexTip = try observation.recognizedPoint(.indexTip)

guard thumbTip.confidence > 0.5, indexTip.confidence > 0.5 else {
    return
}

let distance = hypot(
    thumbTip.location.x - indexTip.location.x,
    thumbTip.location.y - indexTip.location.y
)

let isPinching = distance < 0.05  // Normalized threshold

let chirality = observation.chirality  // .left or .right or .unknown

let request = VNDetectHumanBodyPoseRequest()
try handler.perform([request])

for observation in request.results as? [VNHumanBodyPoseObservation] ?? [] {
    // Process each person
}

// Get all body points
let allPoints = try observation.recognizedPoints(.all)

// Get left arm only
let leftArmPoints = try observation.recognizedPoints(.leftArm)

// Get specific joint
let leftWrist = try observation.recognizedPoint(.leftWrist)

let request = VNDetectHumanBodyPose3DRequest()
try handler.perform([request])

guard let observation = request.results?.first as? VNHumanBodyPose3DObservation else {
    return
}

// Get 3D joint position
let leftWrist = try observation.recognizedPoint(.leftWrist)
let position = leftWrist.position  // simd_float4x4 matrix
let localPosition = leftWrist.localPosition  // Relative to parent joint

let wrist2D = try observation.pointInImage(leftWrist)

// Position relative to skeleton root (center of hip)
let modelPosition = leftWrist.position

// Position relative to parent joint (left elbow)
let relativePosition = leftWrist.localPosition

// From AVDepthData
let handler = VNImageRequestHandler(
    cvPixelBuffer: imageBuffer,
    depthData: depthData,
    orientation: orientation
)

// From file (automatic depth extraction)
let handler = VNImageRequestHandler(url: imageURL)  // Depth auto-fetched

let request = VNDetectFaceRectanglesRequest()
try handler.perform([request])

for observation in request.results as? [VNFaceObservation] ?? [] {
    let faceBounds = observation.boundingBox  // Normalized rect
}

let request = VNDetectFaceLandmarksRequest()
try handler.perform([request])

for observation in request.results as? [VNFaceObservation] ?? [] {
    if let landmarks = observation.landmarks {
        let leftEye = landmarks.leftEye
        let nose = landmarks.nose
        let leftPupil = landmarks.leftPupil  // Revision 2+
    }
}

let request = VNDetectHumanRectanglesRequest()
try handler.perform([request])

for observation in request.results as? [VNHumanObservation] ?? [] {
    let humanBounds = observation.boundingBox  // Normalized rect
}

// 1. Get mask from Vision
let observation = request.results?.first as? VNInstanceMaskObservation
let visionMask = try observation.createScaledMask(
    for: observation.allInstances,
    croppedToInstancesContent: false
)

// 2. Convert to CIImage
let maskImage = CIImage(cvPixelBuffer: axiom-visionMask)

// 3. Apply filter
let filter = CIFilter(name: "CIBlendWithMask")!
filter.setValue(sourceImage, forKey: kCIInputImageKey)
filter.setValue(maskImage, forKey: kCIInputMaskImageKey)
filter.setValue(newBackground, forKey: kCIInputBackgroundImageKey)

let output = filter.outputImage  // Composited result

let request = VNRecognizeTextRequest()
request.recognitionLevel = .accurate  // Or .fast
request.recognitionLanguages = ["en-US", "de-DE"]  // Order matters
request.usesLanguageCorrection = true

let handler = VNImageRequestHandler(cgImage: image)
try handler.perform([request])

for observation in request.results as? [VNRecognizedTextObservation] ?? [] {
    // Get top candidates
    let candidates = observation.topCandidates(3)
    let bestText = candidates.first?.string ?? ""
}

// Check supported languages for current settings
let languages = try VNRecognizeTextRequest.supportedRecognitionLanguages(
    for: .accurate,
    revision: VNRecognizeTextRequestRevision3
)

// Get bounding box for substring
let text = candidate.string
if let range = text.range(of: "invoice") {
    let box = try candidate.boundingBox(for: range)
}

let request = VNDetectBarcodesRequest()
request.symbologies = [.qr, .ean13, .code128]  // Specific codes

let handler = VNImageRequestHandler(cgImage: image)
try handler.perform([request])

for barcode in request.results as? [VNBarcodeObservation] ?? [] {
    let payload = barcode.payloadStringValue
    let type = barcode.symbology
    let bounds = barcode.boundingBox
}

// Hardware support
DataScannerViewController.isSupported

// Runtime availability (camera access, parental controls)
DataScannerViewController.isAvailable

import VisionKit

let dataTypes: Set<DataScannerViewController.RecognizedDataType> = [
    .barcode(symbologies: [.qr, .ean13]),
    .text(textContentType: .URL),  // Or nil for all text
    // .text(languages: ["ja"])  // Filter by language
]

let scanner = DataScannerViewController(
    recognizedDataTypes: dataTypes,
    qualityLevel: .balanced,  // .fast, .balanced, .accurate
    recognizesMultipleItems: true,
    isHighFrameRateTrackingEnabled: true,
    isPinchToZoomEnabled: true,
    isGuidanceEnabled: true,
    isHighlightingEnabled: true
)

scanner.delegate = self
present(scanner, animated: true) {
    try? scanner.startScanning()
}

protocol DataScannerViewControllerDelegate {
    func dataScanner(_ dataScanner: DataScannerViewController,
                     didTapOn item: RecognizedItem)

    func dataScanner(_ dataScanner: DataScannerViewController,
                     didAdd addedItems: [RecognizedItem],
                     allItems: [RecognizedItem])

    func dataScanner(_ dataScanner: DataScannerViewController,
                     didUpdate updatedItems: [RecognizedItem],
                     allItems: [RecognizedItem])

    func dataScanner(_ dataScanner: DataScannerViewController,
                     didRemove removedItems: [RecognizedItem],
                     allItems: [RecognizedItem])

    func dataScanner(_ dataScanner: DataScannerViewController,
                     becameUnavailableWithError error: DataScannerViewController.ScanningUnavailable)
}

enum RecognizedItem {
    case text(RecognizedItem.Text)
    case barcode(RecognizedItem.Barcode)

    var id: UUID { get }
    var bounds: RecognizedItem.Bounds { get }
}

// Text item
struct Text {
    let transcript: String
}

// Barcode item
struct Barcode {
    let payloadStringValue: String?
    let observation: VNBarcodeObservation
}

// Alternative to delegate
for await items in scanner.recognizedItems {
    // Current recognized items
}

// Add custom views over recognized items
scanner.overlayContainerView.addSubview(customHighlight)

// Capture still photo
let photo = try await scanner.capturePhoto()

import VisionKit

let camera = VNDocumentCameraViewController()
camera.delegate = self
present(camera, animated: true)

protocol VNDocumentCameraViewControllerDelegate {
    func documentCameraViewController(_ controller: VNDocumentCameraViewController,
                                       didFinishWith scan: VNDocumentCameraScan)

    func documentCameraViewControllerDidCancel(_ controller: VNDocumentCameraViewController)

    func documentCameraViewController(_ controller: VNDocumentCameraViewController,
                                       didFailWithError error: Error)
}

func documentCameraViewController(_ controller: VNDocumentCameraViewController,
                                   didFinishWith scan: VNDocumentCameraScan) {
    controller.dismiss(animated: true)

    for i in 0..<scan.pageCount {
        let pageImage = scan.imageOfPage(at: i)
        // Process with VNRecognizeTextRequest
    }
}

let request = VNDetectDocumentSegmentationRequest()
let handler = VNImageRequestHandler(ciImage: image)
try handler.perform([request])

guard let observation = request.results?.first as? VNRectangleObservation else {
    return  // No document found
}

// Get corner points (normalized)
let corners = [
    observation.topLeft,
    observation.topRight,
    observation.bottomLeft,
    observation.bottomRight
]

let request = RecognizeDocumentsRequest()
let observations = try await request.perform(on: imageData)

guard let document = observations.first?.document else {
    return
}

DocumentObservation
└── document: DocumentObservation.Document
    ├── text: TextObservation
    ├── tables: [Container.Table]
    ├── lists: [Container.List]
    └── barcodes: [Container.Barcode]

for table in document.tables {
    for row in table.rows {
        for cell in row {
            let text = cell.content.text.transcript
            let detectedData = cell.content.text.detectedData
        }
    }
}

for data in document.text.detectedData {
    switch data.match.details {
    case .emailAddress(let email):
        let address = email.emailAddress
    case .phoneNumber(let phone):
        let number = phone.phoneNumber
    case .link(let url):
        let link = url
    case .address(let address):
        let components = address
    case .date(let date):
        let dateValue = date
    default:
        break
    }
}

TextObservation
├── transcript: String
├── lines: [TextObservation.Line]
├── paragraphs: [TextObservation.Paragraph]
├── words: [TextObservation.Word]
└── detectedData: [DetectedDataObservation]