Make faces big by Vision and CoreGraphics

Transcript

1. Make faces big by Vision and CoreGraphics VisionͱCoreGraphicsͰإΛσΧ͘͢Δ Naruki Chigira,

   Timers inc. @naruchigi Try! Swift 2018

2. “Can you make faces big?”

3. “In about a week.”

4. None

5. Core Image want actual

6. Core ML too much learning cost (also for me) …

7. Vision

8. Vision ɾFace Detection and Recognition ɾBarcode Detection ɾText Detection ɾHorizon

   Detection ɾObject Detection and Tracking

9. VNFaceLandmarkRegion2D Class 2D geometry information for a specific facial feature.

   VNFaceObservation Class Face or facial-feature information detected by an image analysis request.

10. Face Couture [CGPoint]

11. // 1. Create VNDetectFaceLandmarksRequest let request = VNDetectFaceLandmarksRequest() { (request,

    error) in guard let results = request.results else { return } let faceObservations = results.flatMap({ $0 as? VNFaceObservation }) // 3. Handle results // … } // 2. Create VNImageRequestHandler and perform let handler = VNImageRequestHandler(cgImage: cgImage, options: [:]) try! handler.perform([request]) How to get VNFaceLandmarkRegion2D

12. Face Couture

13. None
14. None
15. None
16. None
17. None

18. Core Graphics

19. CGPoint Structure A structure that contains a point in a

    two-dimensional coordinate system.

20. CGAffineTransform Structure An affine transformation matrix for use in drawing

    2D graphics.

21. CGPoint Structure Instance Method func applying(_ t: CGAffineTransform) -> CGPoint

22. O

23. O 1. translate

24. O 1. translate 2. rotate

25. O 1. translate 2. rotate 3. reverse + joint

26. O 1. translate 2. rotate 3. reverse + joint 4.

    rotate-1

27. O 1. translate 2. rotate 3. reverse + joint 4.

    rotate-1 5. translate-1

28. O A A-1 } } 1. translate 2. rotate 3.

    reverse + joint 4. rotate-1 5. translate-1

29. Modify [CGPoint] in Swift // 1. Create CGAffineTransform A let

    A = CGAffineTransform(rotationAngle: -theta).translatedBy(x: x, y: y) // 2. Apply A let transformed = points.map { $0.applying(A) } // 3. Reverse & Joint let oval = transformed + transformed.map { CGPoint(x: -$0.x, y: -$0.y) } // 4. Apply A-1 let result = oval.map { $0.applying(A.inverted()) }

30. Result

31. None
32. None

33. Summary Get facial features from Vision (iOS 11.0~) Process data

    using CoreGraphics (iOS 2.0~) +

34. Thank you!