用相机进行人脸检测

Question

如何像"相机"那样实时进行人脸检测？

我注意到,AVCaptureStillImageOutput为10.0后弃用,因此我用 AVCapturePhotoOutput代替.但是,我发现我为面部检测保存的图像并不那么令人满意？有任何想法吗？

---

UPDATE

在尝试了@Shravya Boggarapu之后提到.目前,我AVCaptureMetadataOutput用来检测脸部没有CIFaceDetector.它按预期工作.然而,当我试图画出脸部的边界时,似乎错位了.任何的想法？

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)
    }

和

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)
            }
        }
    }

}
}

---

原版的

在Github看到

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与正常图像的作品.但是,我通过相机拍摄的图像不起作用,或者有时只能识别一张脸.

正常图像

捕获图像

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)

}

Answer 1

检测面部有两种方法:一种是CIFaceDetector,另一种是AVCaptureMetadataOutput

根据您的要求,选择与您相关的内容.

CIFaceDetector具有更多功能 - 例如:为您提供眼睛和嘴巴的位置,微笑探测器等

另一方面,AVCaptureMetadataOutput是在帧上计算的,并且跟踪检测到的面部,并且我们不需要添加额外的代码.我发现,由于跟踪面在此过程中被更可靠地检测到.这个问题是你只需要检测面部,没有眼睛/嘴巴的位置.此方法的另一个优点是方向问题较小,因为只要更改设备方向并且面的方向将相对于该方向,您就可以使用videoOrientation

在我的情况下,我的应用程序使用YUV420作为所需的格式,因此使用CIDetector(与RGB一起使用)是不可行的.使用AVCaptureMetadataOutput节省了大量精力,并且由于连续跟踪而更可靠地执行.

一旦我有了面部的边界框,我编写了额外的功能,例如皮肤检测,并将其应用于静止图像.

注意:捕获静止图像时,面板信息将与元数据一起添加,因此不会出现同步问题.

您还可以使用两者的组合来获得更好的结果.

根据您的应用,探索和评估优缺点.

UPDATE

面矩形是wrt图像的起源.因此,对于屏幕,它可能会有所不同.使用以下内容:

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 */
}

Answer 2

要在iOS上执行面部检测,可以使用CIDetector(Apple)或Mobile Vision(Google)API.

IMO,Google Mobile Vision提供了更好的性能.

如果您有兴趣,这是您可以玩的项目.(iOS 10.2,Swift 3)

WWDC 2017年后,苹果公司推出CoreML在iOS的11 视觉框架,使脸部检测更准确:)

我做了一个演示项目.包含Vision vs CIDetector.此外,它还包含实时的面部地标检测.