How can I do face detection in realtime just as "Camera" does?
I noticed that AVCaptureStillImageOutput is deprecated after 10.0, so I use AVCapturePhotoOutput instead. However, I found that the image I saved for facial detection is not so satisfied? Any ideas?
UPDATE
After giving a try of @Shravya Boggarapu mentioned. Currently, I use AVCaptureMetadataOutput to detect the face without CIFaceDetector. It works as expected. However, when I'm trying to draw bounds of the face, it seems mislocated. Any idea?
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)
}
and
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)
}
}
}
}
}
Original
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!)
}
}
The findFace works with normal image. However, the image I capture via camera will not work or sometimes only recognize one face.
Normal Image
Capture Image
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)
}
There are 2 ways to go about detecting faces: One is CIFaceDetector and the other is AVCaptureMetadataOutput
Depending on your requirements, choose what is relevant for you.
CIFaceDetector has more features- Eg: Gives you location of eyes and mouth, smile detector, etc
On the other hand, AVCaptureMetadataOutput is computed on the frames and the detected faces are tracked and there is not extra code needed to be added by us. I find that because of the tracking faces are detected more reliably in this process. The con of this is that you will simply detect faces, no position of eyes/mouth. Another advantage of this method is that orientation issues are lesser as you can videoOrientation whenever the device orientation is changed and the orientation of the faces will be relative to that orientation
In my case, my application uses YUV420 as the required format so using CIDetector (which works with RGB) in real-time was not viable. Using AVCaptureMetadataOutput saved a lot of effort and performed more reliably due to continuous tracking.
Once I had the bounding box for the faces, I coded extra features, such as skin detection and applied it on still image.
Note: When you capture still image, the face box information is added along with the metadata so, no sync issues.
You can also use a combination of the two to get better results.
Do explore and evaluate the pros and cons as per your application.
UPDATE
Face rectangle is wrt image origin. So for the screen, it may be different. Use the following:
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 */
}
To perform face detection on iOS, there are either CIDetector (Apple) or Mobile Vision (Google) API.
IMO, Google Mobile Vision provides better performance.
If you are interested, here is the project you can play with. (iOS 10.2, Swift 3)
After WWDC 2017, Apple introduces CoreML in iOS 11. The Vision framework makes the face detection more accurate :)
I've made a Demo Project. containing Vision v.s. CIDetector. Also, it contains face landmarks detection in real time.
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)
}
}
}
}
Be sure to remove the views created by didOutputMetadataObjects.
Keeping track of the active facial ids is the best way to do this ^
Also when you're trying to find the location of faces for your preview layer, it is much easier to use facial data and transform. Also I think CIDetector is junk, metadataoutput will use hardware stuff for face detection making it really fast.
A bit late, but here it is the solution for the coordinates problem. There is a method you can call on the preview layer to transform the metadata object to your coordinate system: transformedMetadataObject(for: metadataObject).
guard let transformedObject = previewLayer.transformedMetadataObject(for: metadataObject) else {
continue
}
let bounds = transformedObject.bounds
showBounds(at: bounds)
By the way, in case you are using (or upgrade your project to) Swift 4, the delegate method of AVCaptureMetadataOutputsObject has change into:
func metadataOutput(_ output: AVCaptureMetadataOutput, didOutput metadataObjects: [AVMetadataObject], from connection: AVCaptureConnection)
Kind regards
- Create CaptureSession
For AVCaptureVideoDataOutput create following settings
output.videoSettings = [ kCVPixelBufferPixelFormatTypeKey as AnyHashable: Int(kCMPixelFormat_32BGRA) ]
3.When you receive CMSampleBuffer, create image
DispatchQueue.main.async {
let sampleImg = self.imageFromSampleBuffer(sampleBuffer: sampleBuffer)
self.imageView.image = sampleImg
}
func imageFromSampleBuffer(sampleBuffer : CMSampleBuffer) -> UIImage
{
// Get a CMSampleBuffer's 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);
}
By looking at your code I detected 2 things that could lead to wrong/poor face detection.
- One of them is the face detector features options where you are filtering the results by
[CIDetectorSmile: true, CIDetectorEyeBlink: true]. Try to set it to nil:faceDetector?.features(in: faceImage, options: nil) - Another guess I have is the result image orientation. I noticed you use
AVCapturePhotoOutput.jpegPhotoDataRepresentationmethod to generate the source image for the detection and the system, by default, it generates that image with a specific orientation, of typeLeft/LandscapeLeft, I think. So, basically you can tell the face detector to have that in mind by using theCIDetectorImageOrientationkey.
CIDetectorImageOrientation: the value for this key is an integer
NSNumberfrom 1..8 such as that found inkCGImagePropertyOrientation. If present, the detection will be done based on that orientation but the coordinates in the returned features will still be based on those of the image.
Try to set it like faceDetector?.features(in: faceImage, options: [CIDetectorImageOrientation: 8 /*Left, bottom*/]).
来源：https://stackoverflow.com/questions/41354698/face-detection-with-camera