face detect in ios

Ref : http://www.appcoda.com/face-detection-core-image/


ios_application/Face_Detector_starter

There are a couple of issues that we haven’t dealt with in the current implementation:

• The face detection is applied on the original image, which has a higher resolution than the image view. And we have set the content mode of the image view to aspect fit. To draw the rectangle properly, we have to calculate the actual position and size of the face in the image view.
• Furthermore, Core Image and UIView (or UIKit) use two different coordinate systems (see the figure below). We have to provide an implementation to translate the Core Image coordinates to UIView coordinates.

因為swift 版本演進...  網站上的code 有 error...

下面這個是ok的

  @IBOutlet weak var personPic: UIImageView!

func detect() {

        

        guard let personciImage = CIImage(image: personPic.image!) else {

            return

        }

        

        let accuracy = [CIDetectorAccuracy: CIDetectorAccuracyHigh]

        let faceDetector = CIDetector(ofType: CIDetectorTypeFace, context: nil, options: accuracy)

        //let faces = faceDetector?.features(in: personciImage)

       let faces = faceDetector?.features(in: personciImage, options: [CIDetectorSmile: true, CIDetectorEyeBlink: true])

        // For converting the Core Image Coordinates to UIView Coordinates

        let ciImageSize = personciImage.extent.size

        var transform = CGAffineTransform(scaleX: 1, y: -1)

        transform = transform.translatedBy(x: 0, y: -ciImageSize.height)

        

        

        for face in faces as! [CIFaceFeature] {

            

            print("Found bounds are \(face.bounds)")

            

            // 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 = personPic.bounds.size

            let scale = min(viewSize.width / ciImageSize.width,

                            viewSize.height / ciImageSize.height)

            let offsetX = (viewSize.width - ciImageSize.width * scale) / 2

            let offsetY = (viewSize.height - ciImageSize.height * scale) / 2

            

            faceViewBounds = faceViewBounds.applying(CGAffineTransform(scaleX: scale, y: scale))

            faceViewBounds.origin.x += offsetX

            faceViewBounds.origin.y += offsetY

            

            let faceBox = UIView(frame: faceViewBounds)

            

          

            

            faceBox.layer.borderWidth = 3

            faceBox.layer.borderColor = UIColor.red.cgColor

            faceBox.backgroundColor = UIColor.clear

            personPic.addSubview(faceBox)

            

            if face.hasLeftEyePosition {

                print("Left eye bounds are \(face.leftEyePosition)")

            }

            

            if face.hasRightEyePosition {

                print("Right eye bounds are \(face.rightEyePosition)")

            }

        }

    }

接下來是整合camera

Building a Camera App with Face Detection

Let’s imagine you have a camera/photo app that takes a photo. As soon as the image is taken you want to run face detection to determine if a face is or is not present. If any given face is present, you might want to classify that photo with some tags or so. While we’re not here to build a photo storing app, we will experiment with a live camera app. To do so, we’ll need to integrate with the UIImagePicker class and run our Face Detection code immediately after a photo is taken.

In the starter project, I have already created the CameraViewController class. Update the code like this to implement the camera feature:

Info.plist must contain an NSCameraUsageDescription key