iOS Vision framework｜WWDC 24でSwift強化を解説—Vision framework最新機能を徹底レビュー

// サポートされている言語一覧
if #available(iOS 18.0, *) {
  print(RecognizeTextRequest().supportedRecognitionLanguages.map { "\($0.languageCode!)-\(($0.region?.identifier ?? $0.script?.identifier)!)" })
} else {
  print(try! VNRecognizeTextRequest().supportedRecognitionLanguages())
}

// 実際に使用可能な認識言語はこちらが基準です。
// 実機テストでiOS 18の出力結果：
// ["en-US", "fr-FR", "it-IT", "de-DE", "es-ES", "pt-BR", "zh-Hans", "zh-Hant", "yue-Hans", "yue-Hant", "ko-KR", "ja-JP", "ru-RU", "uk-UA", "th-TH", "vi-VT", "ar-SA", "ars-SA"]
// WWDCで言及されたSwedish言語は見当たりません。まだリリースされていないか、デバイスの地域・言語設定に関連している可能性があります。

let request = CalculateImageAestheticsScoresRequest()
let result = try await request.perform(on: URL(string: "https://zhgchg.li/assets/cb65fd5ab770/1*yL3vI1ADzwlovctW5WQgJw.jpeg")!)

// 写真のスコア
print(result.overallScore)

// 素材画像と判定されたかどうか
print(result.isUtility)

var request = DetectHumanBodyPoseRequest()
// 手のポーズも同時に検出する
request.detectsHands = true

guard let bodyPose = try await request.perform(on: image).first else { return }

// 体のポーズの関節
let bodyJoints = bodyPose.allJoints()
// 左手のポーズの関節
let leftHandJoints = bodyPose.leftHand.allJoints()
// 右手のポーズの関節
let rightHandJoints = bodyPose.rightHand.allJoints()

if #available(iOS 18.0, *) {
    // Swiftの新機能を使った新しいAPI
    let request = ClassifyImageRequest()
    Task {
        do {
            let observations = try await request.perform(on: URL(string: "https://zhgchg.li/assets/cb65fd5ab770/1*yL3vI1ADzwlovctW5WQgJw.jpeg")!)
            observations.forEach {
                observation in
                print("\(observation.identifier): \(observation.confidence)")
            }
        }
        catch {
            print("リクエスト失敗: \(error)")
        }
    }
} else {
    // 以前の書き方
    let completionHandler: VNRequestCompletionHandler = {
        request, error in
        guard error == nil else {
            print("リクエスト失敗: \(String(describing: error))")
            return
        }
        guard let observations = request.results as? [VNClassificationObservation] else {
            return
        }
        observations.forEach {
            observation in
            print("\(observation.identifier): \(observation.confidence)")
        }
    }

    let request = VNClassifyImageRequest(completionHandler: completionHandler)
    DispatchQueue.global().async {
        let handler = VNImageRequestHandler(url: URL(string: "https://zhgchg.li/assets/cb65fd5ab770/1*3_jdrLurFuUfNdW4BJaRww.jpeg")!, options: [:])
        do {
            try handler.perform([request])
        }
        catch {
            print("リクエスト失敗: \(error)")
        }
    }
}

if #available(iOS 18.0, *) {
    // Swiftの新機能を使った新しいAPI
    var request = RecognizeTextRequest()
    request.recognitionLevel = .accurate
    request.recognitionLanguages = [.init(identifier: "ja-JP"), .init(identifier: "en-US")] // 言語コードを指定、例：繁体字中国語
    Task {
        do {
            let observations = try await request.perform(on: URL(string: "https://zhgchg.li/assets/9da2c51fa4f2/1*fBbNbDepYioQ-3-0XUkF6Q.jpeg")!)
            observations.forEach {
                observation in
                let topCandidate = observation.topCandidates(1).first
                print(topCandidate?.string ?? "テキストが認識されませんでした")
            }
        }
        catch {
            print("リクエスト失敗: \(error)")
        }
    }
} else {
    // 旧APIの書き方
    let completionHandler: VNRequestCompletionHandler = {
        request, error in
        guard error == nil else {
            print("リクエスト失敗: \(String(describing: error))")
            return
        }
        guard let observations = request.results as? [VNRecognizedTextObservation] else {
            return
        }
        observations.forEach {
            observation in
            let topCandidate = observation.topCandidates(1).first
            print(topCandidate?.string ?? "テキストが認識されませんでした")
        }
    }

    let request = VNRecognizeTextRequest(completionHandler: completionHandler)
    request.recognitionLevel = .accurate
    request.recognitionLanguages = ["ja-JP", "en-US"] // 言語コードを指定、例：繁体字中国語
    DispatchQueue.global().async {
        let handler = VNImageRequestHandler(url: URL(string: "https://zhgchg.li/assets/9da2c51fa4f2/1*fBbNbDepYioQ-3-0XUkF6Q.jpeg")!, options: [:])
        do {
            try handler.perform([request])
        }
        catch {
            print("リクエスト失敗: \(error)")
        }
    }
}

let filePath = Bundle.main.path(forResource: "IMG_6777", ofType: "png")! // ローカルテスト画像
let fileURL = URL(filePath: filePath)
if #available(iOS 18.0, *) {
    // Swiftの新機能を使った新しいAPI
    let request = DetectBarcodesRequest()
    Task {
        do {
            let observations = try await request.perform(on: fileURL)
            observations.forEach {
                observation in
                print("Payload: \(observation.payloadString ?? "ペイロードなし")")
                print("Symbology: \(observation.symbology)")
            }
        }
        catch {
            print("リクエスト失敗: \(error)")
        }
    }
} else {
    // 旧方式
    let completionHandler: VNRequestCompletionHandler = {
        request, error in
        guard error == nil else {
            print("リクエスト失敗: \(String(describing: error))")
            return
        }
        guard let observations = request.results as? [VNBarcodeObservation] else {
            return
        }
        observations.forEach {
            observation in
            print("Payload: \(observation.payloadStringValue ?? "ペイロードなし")")
            print("Symbology: \(observation.symbology.rawValue)")
        }
    }

    let request = VNDetectBarcodesRequest(completionHandler: completionHandler)
    DispatchQueue.global().async {
        let handler = VNImageRequestHandler(url: fileURL, options: [:])
        do {
            try handler.perform([request])
        }
        catch {
            print("リクエスト失敗: \(error)")
        }
    }
}

let filePath = Bundle.main.path(forResource: "IMG_5026", ofType: "png")! // ローカルテスト画像
let fileURL = URL(filePath: filePath)
if #available(iOS 18.0, *) {
    // Swiftの新機能を使った新しいAPI
    let request = RecognizeAnimalsRequest()
    Task {
        do {
            let observations = try await request.perform(on: fileURL)
            observations.forEach {
                observation in
                let labels = observation.labels
                labels.forEach {
                    label in
                    print("検出された動物: \(label.identifier)、信頼度: \(label.confidence)")
                }
            }
        }
        catch {
            print("リクエスト失敗: \(error)")
        }
    }
} else {
    // 旧APIの書き方
    let completionHandler: VNRequestCompletionHandler = {
        request, error in
        guard error == nil else {
            print("リクエスト失敗: \(String(describing: error))")
            return
        }
        guard let observations = request.results as? [VNRecognizedObjectObservation] else {
            return
        }
        observations.forEach {
            observation in
            let labels = observation.labels
            labels.forEach {
                label in
                print("検出された動物: \(label.identifier)、信頼度: \(label.confidence)")
            }
        }
    }

    let request = VNRecognizeAnimalsRequest(completionHandler: completionHandler)
    DispatchQueue.global().async {
        let handler = VNImageRequestHandler(url: fileURL, options: [:])
        do {
            try handler.perform([request])
        }
        catch {
            print("リクエスト失敗: \(error)")
        }
    }
}

let filePath = Bundle.main.path(forResource: "IMG_6785", ofType: "png")! // ローカルテスト画像
let fileURL = URL(filePath: filePath)
if #available(iOS 18.0, *) {
    // Swiftの新機能を使った新しいAPI
    var request = DetectBarcodesRequest()
    request.symbologies = [.ean13] // EAN13バーコードのみをスキャンする場合は直接指定してパフォーマンス向上
    Task {
        do {
            let observations = try await request.perform(on: fileURL)
            if let observation = observations.first {
                DispatchQueue.main.async {
                    self.infoLabel.text = observation.payloadString
                    // マーク用の色レイヤー
                    let colorLayer = CALayer()
                    // iOS >=18 新しい座標変換API toImageCoordinates
                    // 未検証で、実際にはContentMode = AspectFitのオフセット計算が必要かも:
                    colorLayer.frame = observation.boundingBox.toImageCoordinates(self.baseImageView.frame.size, origin: .upperLeft)
                    colorLayer.backgroundColor = UIColor.red.withAlphaComponent(0.5).cgColor
                    self.baseImageView.layer.addSublayer(colorLayer)
                }
                print("BoundingBox: \(observation.boundingBox.cgRect)")
                print("Payload: \(observation.payloadString ?? "No payload")")
                print("Symbology: \(observation.symbology)")
            }
        }
        catch {
            print("Request failed: \(error)")
        }
    }
} else {
    // 旧APIの書き方
    let completionHandler: VNRequestCompletionHandler = {
        request, error in
        guard error == nil else {
            print("Request failed: \(String(describing: error))")
            return
        }
        guard let observations = request.results as? [VNBarcodeObservation] else {
            return
        }
        if let observation = observations.first {
            DispatchQueue.main.async {
                self.infoLabel.text = observation.payloadStringValue
                // マーク用の色レイヤー
                let colorLayer = CALayer()
                colorLayer.frame = self.convertBoundingBox(observation.boundingBox, to: self.baseImageView)
                colorLayer.backgroundColor = UIColor.red.withAlphaComponent(0.5).cgColor
                self.baseImageView.layer.addSublayer(colorLayer)
            }
            print("BoundingBox: \(observation.boundingBox)")
            print("Payload: \(observation.payloadStringValue ?? "No payload")")
            print("Symbology: \(observation.symbology.rawValue)")
        }
    }

    let request = VNDetectBarcodesRequest(completionHandler: completionHandler)
    request.symbologies = [.ean13] // EAN13バーコードのみをスキャンする場合は直接指定してパフォーマンス向上
    DispatchQueue.global().async {
        let handler = VNImageRequestHandler(url: fileURL, options: [:])
        do {
            try handler.perform([request])
        }
        catch {
            print("Request failed: \(error)")
        }
    }
}

// ChatGPT 4oによって生成
// 画像がImageViewでContentMode = AspectFitに設定されているため
// Fitによってできる上下の空白のオフセットを計算する必要がある
func convertBoundingBox(_ boundingBox: CGRect, to view: UIImageView) -> CGRect {
    guard let image = view.image else {
        return .zero
    }

    let imageSize = image.size
    let viewSize = view.bounds.size
    let imageRatio = imageSize.width / imageSize.height
    let viewRatio = viewSize.width / viewSize.height
    var scaleFactor: CGFloat
    var offsetX: CGFloat = 0
    var offsetY: CGFloat = 0
    if imageRatio > viewRatio {
        // 画像は幅方向にフィットしている
        scaleFactor = viewSize.width / imageSize.width
        offsetY = (viewSize.height - imageSize.height * scaleFactor) / 2
    }

    else {
        // 画像は高さ方向にフィットしている
        scaleFactor = viewSize.height / imageSize.height
        offsetX = (viewSize.width - imageSize.width * scaleFactor) / 2
    }

    let x = boundingBox.minX * imageSize.width * scaleFactor + offsetX
    let y = (1 - boundingBox.maxY) * imageSize.height * scaleFactor + offsetY
    let width = boundingBox.width * imageSize.width * scaleFactor
    let height = boundingBox.height * imageSize.height * scaleFactor
    return CGRect(x: x, y: y, width: width, height: height)
}

let filePath = Bundle.main.path(forResource: "apple", ofType: "jpg")! // ローカルテスト画像
let fileURL = URL(filePath: filePath)
if #available(iOS 18.0, *) {
    // Swiftの新機能を使った新しいAPI
    var barcodesRequest = DetectBarcodesRequest()
    barcodesRequest.symbologies = [.ean13] // EAN13バーコードのみスキャンする場合は指定してパフォーマンス向上
    var textRequest = RecognizeTextRequest()
    textRequest.recognitionLanguages = [.init(identifier: "zh-Hnat"), .init(identifier: "en-US")]
    Task {
        do {
            let handler = ImageRequestHandler(fileURL)
            // パラメータパック構文で全リクエストの完了を待つ必要がある
            // let (barcodesObservation, textObservation, ...) = try await handler.perform(barcodesRequest, textRequest, ...)
            let (barcodesObservation, textObservation) = try await handler.perform(barcodesRequest, textRequest)
            if let observation = barcodesObservation.first {
                DispatchQueue.main.async {
                    self.infoLabel.text = observation.payloadString
                    // マーク用の色レイヤー
                    let colorLayer = CALayer()
                    // iOS >=18 新しい座標変換API toImageCoordinates
                    // 未検証で、実際にはContentMode = AspectFitのオフセット計算が必要な可能性あり
                    colorLayer.frame = observation.boundingBox.toImageCoordinates(self.baseImageView.frame.size, origin: .upperLeft)
                    colorLayer.backgroundColor = UIColor.red.withAlphaComponent(0.5).cgColor
                    self.baseImageView.layer.addSublayer(colorLayer)
                }
                print("BoundingBox: \(observation.boundingBox.cgRect)")
                print("Payload: \(observation.payloadString ?? "ペイロードなし")")
                print("Symbology: \(observation.symbology)")
            }
            textObservation.forEach {
                observation in
                let topCandidate = observation.topCandidates(1).first
                print(topCandidate?.string ?? "テキスト認識なし")
            }
        }
        catch {
            print("リクエスト失敗: \(error)")
        }
    }
} else {
    // 以前の書き方
    let barcodesCompletionHandler: VNRequestCompletionHandler = {
        request, error in
        guard error == nil else {
            print("リクエスト失敗: \(String(describing: error))")
            return
        }
        guard let observations = request.results as? [VNBarcodeObservation] else {
            return
        }
        if let observation = observations.first {
            DispatchQueue.main.async {
                self.infoLabel.text = observation.payloadStringValue
                // マーク用の色レイヤー
                let colorLayer = CALayer()
                colorLayer.frame = self.convertBoundingBox(observation.boundingBox, to: self.baseImageView)
                colorLayer.backgroundColor = UIColor.red.withAlphaComponent(0.5).cgColor
                self.baseImageView.layer.addSublayer(colorLayer)
            }
            print("BoundingBox: \(observation.boundingBox)")
            print("Payload: \(observation.payloadStringValue ?? "ペイロードなし")")
            print("Symbology: \(observation.symbology.rawValue)")
        }
    }

    let textCompletionHandler: VNRequestCompletionHandler = {
        request, error in
        guard error == nil else {
            print("リクエスト失敗: \(String(describing: error))")
            return
        }
        guard let observations = request.results as? [VNRecognizedTextObservation] else {
            return
        }
        observations.forEach {
            observation in
            let topCandidate = observation.topCandidates(1).first
            print(topCandidate?.string ?? "テキスト認識なし")
        }
    }

    let barcodesRequest = VNDetectBarcodesRequest(completionHandler: barcodesCompletionHandler)
    barcodesRequest.symbologies = [.ean13] // EAN13バーコードのみスキャンする場合は指定してパフォーマンス向上
    let textRequest = VNRecognizeTextRequest(completionHandler: textCompletionHandler)
    textRequest.recognitionLevel = .accurate
    textRequest.recognitionLanguages = ["en-US"]
    DispatchQueue.global().async {
        let handler = VNImageRequestHandler(url: fileURL, options: [:])
        do {
            try handler.perform([barcodesRequest, textRequest])
        }
        catch {
            print("リクエスト失敗: \(error)")
        }
    }
}

let handler = ImageRequestHandler(fileURL)
// パラメータパック構文で、すべてのリクエストが完了するのを待ってから結果を使用します。
// let (barcodesObservation, textObservation, ...) = try await handler.perform(barcodesRequest, textRequest, ...)
let (barcodesObservation, textObservation) = try await handler.perform(barcodesRequest, textRequest)

if #available(iOS 18.0, *) {
    // Swiftの新機能を使用した新しいAPI
    var barcodesRequest = DetectBarcodesRequest()
    barcodesRequest.symbologies = [.ean13] // EAN13バーコードのみをスキャンする場合は指定してパフォーマンス向上
    var textRequest = RecognizeTextRequest()
    textRequest.recognitionLanguages = [.init(identifier: "zh-Hnat"), .init(identifier: "en-US")]
    Task {
        let handler = ImageRequestHandler(fileURL)
        let observation = handler.performAll([barcodesRequest, textRequest] as [any VisionRequest])
        for try await result in observation {
            switch result {
                case .detectBarcodes(_, let barcodesObservation):
                if let observation = barcodesObservation.first {
                    DispatchQueue.main.async {
                        self.infoLabel.text = observation.payloadString
                        // 色付きレイヤーのマーク
                        let colorLayer = CALayer()
                        // iOS >=18 新しい座標変換API toImageCoordinates
                        // 未検証、実際にはContentMode = AspectFitのオフセット計算が必要かもしれません:
                        colorLayer.frame = observation.boundingBox.toImageCoordinates(self.baseImageView.frame.size, origin: .upperLeft)
                        colorLayer.backgroundColor = UIColor.red.withAlphaComponent(0.5).cgColor
                        self.baseImageView.layer.addSublayer(colorLayer)
                    }
                    print("BoundingBox: \(observation.boundingBox.cgRect)")
                    print("Payload: \(observation.payloadString ?? "No payload")")
                    print("Symbology: \(observation.symbology)")
                }
                case .recognizeText(_, let textObservation):
                textObservation.forEach {
                    observation in
                    let topCandidate = observation.topCandidates(1).first
                    print(topCandidate?.string ?? "認識されたテキストなし")
                }
                default:
                print("認識されない結果: \(result)")
            }
        }
    }
}

func generateThumbnail(url: URL) async throws -> UIImage {
  let request = GenerateAttentionBasedSaliencyImageRequest()
  let saliencyObservation = try await request.perform(on: url)
  return cropImage(url, to: saliencyObservation.salientObjects)
}
    
func generateAllThumbnails() async throws {
  for image in images {
    image.thumbnail = try await generateThumbnail(url: image.url)
  }
}

func generateAllThumbnails() async throws {
  try await withThrowingDiscardingTaskGroup { taskGroup in
    for image in images {
      image.thumbnail = try await generateThumbnail(url: image.url)
     }
  }
}

func generateAllThumbnails() async throws {
    try await withThrowingDiscardingTaskGroup {
        taskGroup in
        // 最大同時実行数は5を超えない
        let maxImageTasks = min(5, images.count)
        // まず5つのタスクを作成
        for index in 0..<maxImageTasks {
            taskGroup.addTask {
                image[index].thumbnail = try await generateThumbnail(url: image[index].url)
            }
        }
        var nextIndex = maxImageTasks
        for try await _ in taskGroup {
            // taskGroup内のタスクが完了した時...
            // インデックスが終端か確認
            if nextIndex < images.count {
                let image = images[nextIndex]
                // タスクを順次追加（最大5つを維持）
                taskGroup.addTask {
                    image.thumbnail = try await generateThumbnail(url: image.url)
                }
                nextIndex += 1
            }
        }
    }
}