如何使用视觉检测器在脸部绘制矢量图像

Question

我想通过使用Vision检测脸部点来绘制脸部的矢量图像我创建了一个代码，其中我得到了一些点，并且我已经下载了绘制线条的代码，但我无法理解它并且自定义线路。请帮助我理解代码，如果有人可以帮助我如何使用我拥有的人脸检测代码在脸上绘制点，我检测人脸的代码是：

          func drawOnImage(source: UIImage,
                             boundingRect: CGRect,
                             faceLandmarkRegions: [VNFaceLandmarkRegion2D]) -> UIImage {
    UIGraphicsBeginImageContextWithOptions(source.size, false, 1)
    let context = UIGraphicsGetCurrentContext()!
    context.translateBy(x: 0, y: source.size.height)
    context.scaleBy(x: 1.0, y: -1.0)
    context.setBlendMode(CGBlendMode.colorBurn)
    context.setLineJoin(.round)
    context.setLineCap(.round)
    context.setShouldAntialias(true)
    context.setAllowsAntialiasing(true)
    
    let rectWidth = source.size.width * boundingRect.size.width
    let rectHeight = source.size.height * boundingRect.size.height
    
    //draw image
    let rect = CGRect(x: 0, y:0, width: source.size.width, height: source.size.height)
    context.draw(source.cgImage!, in: rect)
    
    
    //draw bound rect
    var fillColor = UIColor.green
    fillColor.setFill()
    context.addRect(CGRect(x: boundingRect.origin.x * source.size.width,                  y:boundingRect.origin.y * source.size.height, width: rectWidth, height: rectHeight))
    context.drawPath(using: CGPathDrawingMode.stroke)
    
    //draw overlay
    fillColor = UIColor.red
    fillColor.setStroke()
    context.setLineWidth(2.0)
    for faceLandmarkRegion in faceLandmarkRegions {
        var points: [CGPoint] = []
        for i in 0..<faceLandmarkRegion.pointCount {
            let point = faceLandmarkRegion.normalizedPoints[i]
            let p = CGPoint(x: CGFloat(point.x), y: CGFloat(point.y))
            points.append(p)
        }
        let mappedPoints = points.map { CGPoint(x: boundingRect.origin.x * source.size.width + $0.x * rectWidth, y: boundingRect.origin.y * source.size.height + $0.y * rectHeight) }
        context.addLines(between: mappedPoints)
        context.drawPath(using: CGPathDrawingMode.stroke)
    }
    
    let coloredImg : UIImage = UIGraphicsGetImageFromCurrentImageContext()!
    UIGraphicsEndImageContext()
    return coloredImg
}

我想绘制矢量图像，脸上有点和线

Answer 1

伙计们，我已经使用 ARKit 实现了我想要的输出，它提供了 Face Mask 的功能。我现在可以在检测到的脸上添加面罩，我在这里分享代码。

import ARKit

在类中声明一个属性

let sceneView = ARSCNView()

将以下代码放入ViewDidLoad()类的方法中

let frame = CGRect(x:0, y: 0, width: self.view.frame.size.width, 
height: self.cameraView.bounds.height)
    sceneView.frame = frame
    self.view.addSubview(sceneView)
 sceneView.delegate = self
    guard ARFaceTrackingConfiguration.isSupported else { return }
    let configuration = ARFaceTrackingConfiguration()
    configuration.isLightEstimationEnabled = true
    sceneView.session.run(configuration, options: [.resetTracking, 
    .removeExistingAnchors])

在您的类中添加以下两个委托方法并从ARSCNViewDelegate

继承您的类

func renderer(_ renderer: SCNSceneRenderer, nodeFor anchor: ARAnchor) -> 
SCNNode? {
    
    guard let device = sceneView.device else {
        return nil
    }
    
    let faceGeometry = ARSCNFaceGeometry(device: device)
    let node = SCNNode(geometry: faceGeometry)
    node.geometry?.firstMaterial?.fillMode = .lines
    
    return node
}

func renderer(_ renderer: SCNSceneRenderer, didUpdate node: SCNNode, for 
anchor: ARAnchor) {
    
    guard let faceAnchor = anchor as? ARFaceAnchor,
        let faceGeometry = node.geometry as? ARSCNFaceGeometry else {
            return
    }
    faceGeometry.update(from: faceAnchor.geometry) 
 }

现在，当您运行代码时，您将能够看到检测到的脸部有一个矢量线面罩