What do you need to do?

┌─ Isolate subject(s) from background?
│  ├─ Need system UI + out-of-process → VisionKit
│  │  └─ ImageAnalysisInteraction (iOS/iPadOS)
│  │  └─ ImageAnalysisOverlayView (macOS)
│  ├─ Need custom pipeline / HDR / large images → Vision
│  │  └─ VNGenerateForegroundInstanceMaskRequest
│  └─ Need to EXCLUDE hands from object → Combine APIs
│     └─ Subject mask + Hand pose + custom masking (see Pattern 1)
│
├─ Segment people?
│  ├─ All people in one mask → VNGeneratePersonSegmentationRequest
│  └─ Separate mask per person (up to 4) → VNGeneratePersonInstanceMaskRequest
│
├─ Detect hand pose/gestures?
│  ├─ Just hand location → VNDetectHumanRectanglesRequest
│  └─ 21 hand landmarks → VNDetectHumanHandPoseRequest
│     └─ Gesture recognition → Hand pose + distance checks
│
├─ Detect body pose?
│  ├─ 2D normalized landmarks → VNDetectHumanBodyPoseRequest
│  ├─ 3D real-world coordinates → VNDetectHumanBodyPose3DRequest
│  └─ Action classification → Body pose + CreateML model
│
├─ Face detection?
│  ├─ Just bounding boxes → VNDetectFaceRectanglesRequest
│  └─ Detailed landmarks → VNDetectFaceLandmarksRequest
│
├─ Person detection (location only)?
│  └─ VNDetectHumanRectanglesRequest
│
├─ Recognize text in images?
│  ├─ Real-time from camera + need UI → DataScannerViewController (iOS 16+)
│  ├─ Processing captured image → VNRecognizeTextRequest
│  │  ├─ Need speed (real-time camera) → recognitionLevel = .fast
│  │  └─ Need accuracy (documents) → recognitionLevel = .accurate
│  └─ Need structured documents (iOS 26+) → RecognizeDocumentsRequest
│
├─ Detect barcodes/QR codes?
│  ├─ Real-time camera + need UI → DataScannerViewController (iOS 16+)
│  └─ Processing image → VNDetectBarcodesRequest
│
└─ Scan documents?
   ├─ Need built-in UI + perspective correction → VNDocumentCameraViewController
   ├─ Need structured data (tables, lists) → RecognizeDocumentsRequest (iOS 26+)
   └─ Custom pipeline → VNDetectDocumentSegmentationRequest + perspective correction

let processingQueue = DispatchQueue(label: "com.yourapp.vision", qos: .userInitiated)

processingQueue.async {
    do {
        let request = VNGenerateForegroundInstanceMaskRequest()
        let handler = VNImageRequestHandler(cgImage: image)
        try handler.perform([request])

        // Process observations...

        DispatchQueue.main.async {
            // Update UI
        }
    } catch {
        // Handle error
    }
}

// 1. Get subject instance mask
let subjectRequest = VNGenerateForegroundInstanceMaskRequest()
let handler = VNImageRequestHandler(cgImage: sourceImage)
try handler.perform([subjectRequest])

guard let subjectObservation = subjectRequest.results?.first as? VNInstanceMaskObservation else {
    fatalError("No subject detected")
}

// 2. Get hand pose landmarks
let handRequest = VNDetectHumanHandPoseRequest()
handRequest.maximumHandCount = 2
try handler.perform([handRequest])

guard let handObservation = handRequest.results?.first as? VNHumanHandPoseObservation else {
    // No hand detected - use full subject mask
    let mask = try subjectObservation.createScaledMask(
        for: subjectObservation.allInstances,
        croppedToInstancesContent: false
    )
    return mask
}

// 3. Create hand exclusion region from landmarks
let handPoints = try handObservation.recognizedPoints(.all)
let handBounds = calculateConvexHull(from: handPoints)  // Your implementation

// 4. Subtract hand region from subject mask using CoreImage
let subjectMask = try subjectObservation.createScaledMask(
    for: subjectObservation.allInstances,
    croppedToInstancesContent: false
)

let subjectCIMask = CIImage(cvPixelBuffer: subjectMask)
let handMask = createMaskFromRegion(handBounds, size: sourceImage.size)
let finalMask = subtractMasks(handMask: handMask, from: subjectCIMask)

// 5. Calculate bounding box from final mask
let objectBounds = calculateBoundingBox(from: finalMask)

func calculateConvexHull(from points: [VNRecognizedPointKey: VNRecognizedPoint]) -> CGRect {
    // Get high-confidence points
    let validPoints = points.values.filter { $0.confidence > 0.5 }

    guard !validPoints.isEmpty else { return .zero }

    // Simple bounding rect (for more accuracy, use actual convex hull algorithm)
    let xs = validPoints.map { $0.location.x }
    let ys = validPoints.map { $0.location.y }

    let minX = xs.min()!
    let maxX = xs.max()!
    let minY = ys.min()!
    let maxY = ys.max()!

    return CGRect(
        x: minX,
        y: minY,
        width: maxX - minX,
        height: maxY - minY
    )
}

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

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

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

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

// Get all subjects
for subject in analysis.subjects {
    let subjectImage = subject.image
    let subjectBounds = subject.bounds

    // Process subject...
}

// Tap-based lookup
if let subject = try await analysis.subject(at: tapPoint) {
    let compositeImage = try await analysis.image(for: [subject])
}

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

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

// Get soft segmentation mask
let mask = try observation.createScaledMask(
    for: observation.allInstances,
    croppedToInstancesContent: false  // Full resolution for compositing
)

// Use with CoreImage for HDR preservation
let filter = CIFilter(name: "CIBlendWithMask")!
filter.setValue(CIImage(cgImage: sourceImage), forKey: kCIInputImageKey)
filter.setValue(CIImage(cvPixelBuffer: mask), forKey: kCIInputMaskImageKey)
filter.setValue(newBackground, forKey: kCIInputBackgroundImageKey)

let compositedImage = filter.outputImage

// Get instance at tap point
let instance = observation.instanceAtPoint(tapPoint)

if instance == 0 {
    // Background tapped - select all instances
    let mask = try observation.createScaledMask(
        for: observation.allInstances,
        croppedToInstancesContent: false
    )
} else {
    // Specific instance tapped
    let mask = try observation.createScaledMask(
        for: IndexSet(integer: instance),
        croppedToInstancesContent: true
    )
}

let instanceMask = observation.instanceMask

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

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

// Convert normalized tap to pixel coordinates
let pixelPoint = VNImagePointForNormalizedPoint(
    tapPoint,
    width: imageWidth,
    height: imageHeight
)

let offset = Int(pixelPoint.y) * bytesPerRow + Int(pixelPoint.x)
let label = UnsafeRawPointer(baseAddress!).load(
    fromByteOffset: offset,
    as: UInt8.self
)

let request = VNDetectHumanHandPoseRequest()
request.maximumHandCount = 1

try handler.perform([request])

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

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

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

// Calculate distance (normalized coordinates)
let dx = thumbTip.location.x - indexTip.location.x
let dy = thumbTip.location.y - indexTip.location.y
let distance = sqrt(dx * dx + dy * dy)

let isPinching = distance < 0.05  // Adjust threshold

// State machine for evidence accumulation
if isPinching {
    pinchFrameCount += 1
    if pinchFrameCount >= 3 {
        state = .pinched
    }
} else {
    pinchFrameCount = max(0, pinchFrameCount - 1)
    if pinchFrameCount == 0 {
        state = .apart
    }
}

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

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

let peopleCount = observation.allInstances.count  // Up to 4

for personIndex in observation.allInstances {
    let personMask = try observation.createScaledMask(
        for: IndexSet(integer: personIndex),
        croppedToInstancesContent: false
    )

    // Apply effect to this person only
    applyEffect(to: personMask, personIndex: personIndex)
}

// Count faces to detect crowding
let faceRequest = VNDetectFaceRectanglesRequest()
try handler.perform([faceRequest])

let faceCount = faceRequest.results?.count ?? 0

if faceCount > 4 {
    // Fallback: Use single mask for all people
    let singleMaskRequest = VNGeneratePersonSegmentationRequest()
    try handler.perform([singleMaskRequest])
}

// 1. Collect body pose observations
var poseObservations: [VNHumanBodyPoseObservation] = []

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

if let observation = request.results?.first as? VNHumanBodyPoseObservation {
    poseObservations.append(observation)
}

// 2. When you have 60 frames of poses, prepare for CreateML model
if poseObservations.count == 60 {
    var multiArray = try MLMultiArray(
        shape: [60, 18, 3],  // 60 frames, 18 joints, (x, y, confidence)
        dataType: .double
    )

    for (frameIndex, observation) in poseObservations.enumerated() {
        let allPoints = try observation.recognizedPoints(.all)

        for (jointIndex, (_, point)) in allPoints.enumerated() {
            multiArray[[frameIndex, jointIndex, 0] as [NSNumber]] = NSNumber(value: point.location.x)
            multiArray[[frameIndex, jointIndex, 1] as [NSNumber]] = NSNumber(value: point.location.y)
            multiArray[[frameIndex, jointIndex, 2] as [NSNumber]] = NSNumber(value: point.confidence)
        }
    }

    // 3. Run inference with CreateML model
    let input = YourActionClassifierInput(poses: multiArray)
    let output = try actionClassifier.prediction(input: input)

    let action = output.label  // "jumping_jacks", "squats", etc.
}

let request = VNRecognizeTextRequest()
request.recognitionLevel = .accurate  // Or .fast for real-time
request.recognitionLanguages = ["en-US"]  // Specify known languages
request.usesLanguageCorrection = true  // Helps accuracy

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

guard let observations = request.results as? [VNRecognizedTextObservation] else {
    return
}

for observation in observations {
    // Get top candidate (most likely)
    guard let candidate = observation.topCandidates(1).first else { continue }

    let text = candidate.string
    let confidence = candidate.confidence

    // Get bounding box for specific substring
    if let range = text.range(of: searchTerm) {
        if let boundingBox = try? candidate.boundingBox(for: range) {
            // Use for highlighting
        }
    }
}

let request = VNDetectBarcodesRequest()
request.revision = VNDetectBarcodesRequestRevision3  // ML-based, iOS 16+
request.symbologies = [.qr, .ean13]  // Specify only what you need!

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

guard let observations = request.results as? [VNBarcodeObservation] else {
    return
}

for barcode in observations {
    let payload = barcode.payloadStringValue  // Decoded content
    let symbology = barcode.symbology  // Type of barcode
    let bounds = barcode.boundingBox  // Location (normalized)

    print("Found \(symbology): \(payload ?? "no string")")
}

import VisionKit

// Check support
guard DataScannerViewController.isSupported,
      DataScannerViewController.isAvailable else {
    // Not supported or camera access denied
    return
}

// Configure what to scan
let recognizedDataTypes: Set<DataScannerViewController.RecognizedDataType> = [
    .barcode(symbologies: [.qr]),
    .text(textContentType: .URL)  // Or nil for all text
]

// Create and present
let scanner = DataScannerViewController(
    recognizedDataTypes: recognizedDataTypes,
    qualityLevel: .balanced,  // Or .fast, .accurate
    recognizesMultipleItems: false,  // Center-most if false
    isHighFrameRateTrackingEnabled: true,  // For smooth highlights
    isPinchToZoomEnabled: true,
    isGuidanceEnabled: true,
    isHighlightingEnabled: true
)

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

func dataScanner(_ scanner: DataScannerViewController,
                 didTapOn item: RecognizedItem) {
    switch item {
    case .text(let text):
        print("Tapped text: \(text.transcript)")
    case .barcode(let barcode):
        print("Tapped barcode: \(barcode.payloadStringValue ?? "")")
    @unknown default: break
    }
}

// For custom highlights
func dataScanner(_ scanner: DataScannerViewController,
                 didAdd addedItems: [RecognizedItem],
                 allItems: [RecognizedItem]) {
    for item in addedItems {
        let highlight = createHighlight(for: item)
        scanner.overlayContainerView.addSubview(highlight)
    }
}

for await items in scanner.recognizedItems {
    // Process current items
}

import VisionKit

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

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

    // Process each page
    for pageIndex in 0..<scan.pageCount {
        let image = scan.imageOfPage(at: pageIndex)

        // Now run text recognition on the corrected image
        let handler = VNImageRequestHandler(cgImage: image.cgImage!)
        let textRequest = VNRecognizeTextRequest()
        try? handler.perform([textRequest])
    }
}

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

guard let observation = request.results?.first,
      let document = observation as? VNRectangleObservation else {
    return
}

// Get corner points (normalized coordinates)
let topLeft = document.topLeft
let topRight = document.topRight
let bottomLeft = document.bottomLeft
let bottomRight = document.bottomRight

// Apply perspective correction with CoreImage
let correctedImage = inputImage
    .cropped(to: document.boundingBox.scaled(to: imageSize))
    .applyingFilter("CIPerspectiveCorrection", parameters: [
        "inputTopLeft": CIVector(cgPoint: topLeft.scaled(to: imageSize)),
        "inputTopRight": CIVector(cgPoint: topRight.scaled(to: imageSize)),
        "inputBottomLeft": CIVector(cgPoint: bottomLeft.scaled(to: imageSize)),
        "inputBottomRight": CIVector(cgPoint: bottomRight.scaled(to: imageSize))
    ])

// iOS 26+
let request = RecognizeDocumentsRequest()
let observations = try await request.perform(on: imageData)

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

// Extract tables
for table in document.tables {
    for row in table.rows {
        for cell in row {
            let text = cell.content.text.transcript
            print("Cell: \(text)")
        }
    }
}

// Get detected data (emails, phones, URLs, dates)
let allDetectedData = document.text.detectedData
for data in allDetectedData {
    switch data.match.details {
    case .emailAddress(let email):
        print("Email: \(email.emailAddress)")
    case .phoneNumber(let phone):
        print("Phone: \(phone.phoneNumber)")
    case .link(let url):
        print("URL: \(url)")
    default: break
    }
}

// 1. Use region of interest to guide user
let textRequest = VNRecognizeTextRequest { request, error in
    guard let observations = request.results as? [VNRecognizedTextObservation] else { return }

    for observation in observations {
        guard let candidate = observation.topCandidates(1).first else { continue }

        // Use domain knowledge to filter
        if let phoneNumber = self.extractPhoneNumber(from: candidate.string) {
            self.stringTracker.add(phoneNumber)
        }
    }

    // Build evidence over frames
    if let stableNumber = self.stringTracker.getStableString(threshold: 10) {
        self.foundPhoneNumber(stableNumber)
    }
}

textRequest.recognitionLevel = .fast  // Real-time
textRequest.usesLanguageCorrection = false  // Codes, not natural text
textRequest.regionOfInterest = guidanceBox  // Crop to user's focus area

// 2. String tracker for stability
class StringTracker {
    private var seenStrings: [String: Int] = [:]

    func add(_ string: String) {
        seenStrings[string, default: 0] += 1
    }

    func getStableString(threshold: Int) -> String? {
        seenStrings.first { $0.value >= threshold }?.key
    }
}