Обнаружение лиц с помощью камеры

Как я могу распознавать лицо в реальном времени так же, как "Камера"?

Я заметил, что AVCaptureStillImageOutput устарел после 10.0, поэтому я использую AVCapturePhotoOutput. Однако я обнаружил, что изображение, которое я сохранил для обнаружения лица, не так удовлетворено? Есть идеи?

UPDATE

После того, как попробовал @Шрива Боггарапу, упомянул. В настоящее время я использую AVCaptureMetadataOutput для обнаружения лица без CIFaceDetector. Он работает так, как ожидалось. Однако, когда я пытаюсь нарисовать границы лица, это кажется неправильным. Есть идеи?

let metaDataOutput = AVCaptureMetadataOutput()

captureSession.sessionPreset = AVCaptureSessionPresetPhoto
    let backCamera = AVCaptureDevice.defaultDevice(withDeviceType: .builtInWideAngleCamera, mediaType: AVMediaTypeVideo, position: .back)
    do {
        let input = try AVCaptureDeviceInput(device: backCamera)

        if (captureSession.canAddInput(input)) {
            captureSession.addInput(input)

            // MetadataOutput instead
            if(captureSession.canAddOutput(metaDataOutput)) {
                captureSession.addOutput(metaDataOutput)

                metaDataOutput.setMetadataObjectsDelegate(self, queue: DispatchQueue.main)
                metaDataOutput.metadataObjectTypes = [AVMetadataObjectTypeFace]

                previewLayer = AVCaptureVideoPreviewLayer(session: captureSession)
                previewLayer?.frame = cameraView.bounds
                previewLayer?.videoGravity = AVLayerVideoGravityResizeAspectFill

                cameraView.layer.addSublayer(previewLayer!)
                captureSession.startRunning()
            }

        }

    } catch {
        print(error.localizedDescription)
    }

и

extension CameraViewController: AVCaptureMetadataOutputObjectsDelegate {
func captureOutput(_ captureOutput: AVCaptureOutput!, didOutputMetadataObjects metadataObjects: [Any]!, from connection: AVCaptureConnection!) {
    if findFaceControl {
        findFaceControl = false
        for metadataObject in metadataObjects {
            if (metadataObject as AnyObject).type == AVMetadataObjectTypeFace {
                print("😇😍😎")
                print(metadataObject)
                let bounds = (metadataObject as! AVMetadataFaceObject).bounds
                print("origin x: \(bounds.origin.x)")
                print("origin y: \(bounds.origin.y)")
                print("size width: \(bounds.size.width)")
                print("size height: \(bounds.size.height)")
                print("cameraView width: \(self.cameraView.frame.width)")
                print("cameraView height: \(self.cameraView.frame.height)")
                var face = CGRect()
                face.origin.x = bounds.origin.x * self.cameraView.frame.width
                face.origin.y = bounds.origin.y * self.cameraView.frame.height
                face.size.width = bounds.size.width * self.cameraView.frame.width
                face.size.height = bounds.size.height * self.cameraView.frame.height
                print(face)

                showBounds(at: face)
            }
        }
    }

}
}

Оригинал

см. в Github

var captureSession = AVCaptureSession()
var photoOutput = AVCapturePhotoOutput()
var previewLayer: AVCaptureVideoPreviewLayer?    

override func viewWillAppear(_ animated: Bool) {
    super.viewWillAppear(true)

    captureSession.sessionPreset = AVCaptureSessionPresetHigh

    let backCamera = AVCaptureDevice.defaultDevice(withMediaType: AVMediaTypeVideo)
    do {
        let input = try AVCaptureDeviceInput(device: backCamera)

        if (captureSession.canAddInput(input)) {
            captureSession.addInput(input)

            if(captureSession.canAddOutput(photoOutput)){
                captureSession.addOutput(photoOutput)
                captureSession.startRunning()

                previewLayer = AVCaptureVideoPreviewLayer(session: captureSession)
                previewLayer?.videoGravity = AVLayerVideoGravityResizeAspectFill
                previewLayer?.frame = cameraView.bounds

                cameraView.layer.addSublayer(previewLayer!)
            }
        }

    } catch {
        print(error.localizedDescription)
    }

}

func captureImage() {
    let settings = AVCapturePhotoSettings()
    let previewPixelType = settings.availablePreviewPhotoPixelFormatTypes.first!
    let previewFormat = [kCVPixelBufferPixelFormatTypeKey as String: previewPixelType
                         ]
    settings.previewPhotoFormat = previewFormat
    photoOutput.capturePhoto(with: settings, delegate: self)

}



func capture(_ captureOutput: AVCapturePhotoOutput, didFinishProcessingPhotoSampleBuffer photoSampleBuffer: CMSampleBuffer?, previewPhotoSampleBuffer: CMSampleBuffer?, resolvedSettings: AVCaptureResolvedPhotoSettings, bracketSettings: AVCaptureBracketedStillImageSettings?, error: Error?) {
    if let error = error {
        print(error.localizedDescription)
    }
    // Not include previewPhotoSampleBuffer
    if let sampleBuffer = photoSampleBuffer,
        let dataImage = AVCapturePhotoOutput.jpegPhotoDataRepresentation(forJPEGSampleBuffer: sampleBuffer, previewPhotoSampleBuffer: nil) {
            self.imageView.image = UIImage(data: dataImage)
            self.imageView.isHidden = false
            self.previewLayer?.isHidden = true
            self.findFace(img: self.imageView.image!)
        }
}

findFace работает с обычным изображением. Однако изображение, которое я захватываю с помощью камеры, не работает или иногда распознает только одно лицо.

Нормальное изображение

Захват изображения

func findFace(img: UIImage) {
    guard let faceImage = CIImage(image: img) else { return }
    let accuracy = [CIDetectorAccuracy: CIDetectorAccuracyHigh]
    let faceDetector = CIDetector(ofType: CIDetectorTypeFace, context: nil, options: accuracy)


    // For converting the Core Image Coordinates to UIView Coordinates
    let detectedImageSize = faceImage.extent.size
    var transform = CGAffineTransform(scaleX: 1, y: -1)
    transform = transform.translatedBy(x: 0, y: -detectedImageSize.height)


    if let faces = faceDetector?.features(in: faceImage, options: [CIDetectorSmile: true, CIDetectorEyeBlink: true]) {
        for face in faces as! [CIFaceFeature] {

            // Apply the transform to convert the coordinates
            var faceViewBounds =  face.bounds.applying(transform)
            // Calculate the actual position and size of the rectangle in the image view
            let viewSize = imageView.bounds.size
            let scale = min(viewSize.width / detectedImageSize.width,
                            viewSize.height / detectedImageSize.height)
            let offsetX = (viewSize.width - detectedImageSize.width * scale) / 2
            let offsetY = (viewSize.height - detectedImageSize.height * scale) / 2

            faceViewBounds = faceViewBounds.applying(CGAffineTransform(scaleX: scale, y: scale))
            print("faceBounds = \(faceViewBounds)")
            faceViewBounds.origin.x += offsetX
            faceViewBounds.origin.y += offsetY

            showBounds(at: faceViewBounds)
        }

        if faces.count != 0 {
            print("Number of faces: \(faces.count)")
        } else {
            print("No faces 😢")
        }
    }


}

func showBounds(at bounds: CGRect) {
    let indicator = UIView(frame: bounds)
    indicator.frame =  bounds
    indicator.layer.borderWidth = 3
    indicator.layer.borderColor = UIColor.red.cgColor
    indicator.backgroundColor = .clear

    self.imageView.addSubview(indicator)
    faceBoxes.append(indicator)

}

Ответы

for (AVMetadataFaceObject *faceFeatures in metadataObjects) {
    CGRect face = faceFeatures.bounds;
    CGRect facePreviewBounds = CGRectMake(face.origin.y * previewLayerRect.size.width,
                               face.origin.x * previewLayerRect.size.height,
                               face.size.width * previewLayerRect.size.height,
                               face.size.height * previewLayerRect.size.width);

    /* Draw rectangle facePreviewBounds on screen */
}

DispatchQueue.main.async {
    let sampleImg = self.imageFromSampleBuffer(sampleBuffer: sampleBuffer)
    self.imageView.image = sampleImg
}
func imageFromSampleBuffer(sampleBuffer : CMSampleBuffer) -> UIImage
    {
        // Get a CMSampleBuffer Core Video image buffer for the media data
        let  imageBuffer = CMSampleBufferGetImageBuffer(sampleBuffer);
        // Lock the base address of the pixel buffer
        CVPixelBufferLockBaseAddress(imageBuffer!, CVPixelBufferLockFlags.readOnly);


        // Get the number of bytes per row for the pixel buffer
        let baseAddress = CVPixelBufferGetBaseAddress(imageBuffer!);

        // Get the number of bytes per row for the pixel buffer
        let bytesPerRow = CVPixelBufferGetBytesPerRow(imageBuffer!);
        // Get the pixel buffer width and height
        let width = CVPixelBufferGetWidth(imageBuffer!);
        let height = CVPixelBufferGetHeight(imageBuffer!);

        // Create a device-dependent RGB color space
        let colorSpace = CGColorSpaceCreateDeviceRGB();

        // Create a bitmap graphics context with the sample buffer data
        var bitmapInfo: UInt32 = CGBitmapInfo.byteOrder32Little.rawValue
        bitmapInfo |= CGImageAlphaInfo.premultipliedFirst.rawValue & CGBitmapInfo.alphaInfoMask.rawValue
        //let bitmapInfo: UInt32 = CGBitmapInfo.alphaInfoMask.rawValue
        let context = CGContext.init(data: baseAddress, width: width, height: height, bitsPerComponent: 8, bytesPerRow: bytesPerRow, space: colorSpace, bitmapInfo: bitmapInfo)
        // Create a Quartz image from the pixel data in the bitmap graphics context
        let quartzImage = context?.makeImage();
        // Unlock the pixel buffer
        CVPixelBufferUnlockBaseAddress(imageBuffer!, CVPixelBufferLockFlags.readOnly);

        // Create an image object from the Quartz image
        let image = UIImage.init(cgImage: quartzImage!);

        return (image);
    }

extension CameraViewController: AVCaptureMetadataOutputObjectsDelegate {
  func captureOutput(_ captureOutput: AVCaptureOutput!, didOutputMetadataObjects metadataObjects: [Any]!, from connection: AVCaptureConnection!) {
    if findFaceControl {
      findFaceControl = false
      let faces = metadata.flatMap { $0 as? AVMetadataFaceObject } .flatMap { (face) -> CGRect in
                  guard let localizedFace =
      previewLayer?.transformedMetadataObject(for: face) else { return nil }
                  return localizedFace.bounds }
      for face in faces {
        let temp = UIView(frame: face)
        temp.layer.borderColor = UIColor.white
        temp.layer.borderWidth = 2.0
        view.addSubview(view: temp)
      }
    }
  }
}