使用face-api实现表情识别

文章来自我的公众号：前端打怪记
实验唠嗑：

闲来无事，无意之间发现了一个有意思的npm包，face-api.js，这次小叙将把自己一早上折腾的结果进行记录。在线浏览地址在如下的链接，喜欢的小伙伴可以自行学习尝试，做自己的表情大师。

实验结果：

• 面无表情
  
• 欢乐表情
  
• 生气表情
  
• 惊讶表情
  
• 很烦表情
  
  核心代码：
  html部分

<video id="video" width="620" height="500" autoplay muted ></video>
<script src="face-api.min.js"></script>
<script src="index.js"></script>

2.js部分

//使用Promise异步加载对应的模型
Promise.all([
  faceapi.nets.tinyFaceDetector.loadFromUri('./models'),
  faceapi.nets.faceLandmark68Net.loadFromUri('./models'),
  faceapi.nets.faceRecognitionNet.loadFromUri('./models'),
  faceapi.nets.faceExpressionNet.loadFromUri('./models')
]).then(startVideo)
//让浏览器自动打开摄像头
function startVideo() {
  navigator.getUserMedia(
    { video: {} },
    stream => video.srcObject = stream,
    err => console.error(err)
  )
}
//监听对应的人脸表情和模型数据进行比对
video.addEventListener('play', () => {
  const canvas = faceapi.createCanvasFromMedia(video)
  document.body.append(canvas)
  const displaySize = { width: video.width, height: video.height }
  faceapi.matchDimensions(canvas, displaySize)
  //比对好之后利用canvas进行画图
  setInterval(async () => {
    const detections = await faceapi.detectAllFaces(video, new faceapi.TinyFaceDetectorOptions()).withFaceLandmarks().withFaceExpressions()
    const resizedDetections = faceapi.resizeResults(detections, displaySize)
    canvas.getContext('2d').clearRect(0, 0, canvas.width, canvas.height)
    faceapi.draw.drawDetections(canvas, resizedDetections)
    faceapi.draw.drawFaceLandmarks(canvas, resizedDetections)
    faceapi.draw.drawFaceExpressions(canvas, resizedDetections)
  }, 100)
})

实验参考：

https://www.npmjs.com/package/face-api.js

标签：canvas,const,face,api,video,识别,nets,faceapi,表情
来源： https://blog.csdn.net/ljxzuishuai/article/details/119119035