Adding auto capture on face detection using tracking.js

Question

Need help on adding auto capture/snapshot on face detect. Using this example from tracking.js:

https://github.com/eduardolundgren/tracking.js/blob/master/examples/face_camera.html http://trackingjs.com/examples/face_camera.html

Any idea will be greatly appreciated. Thanks!

Answer 1

I needed this as well. I used this link to help me get to this answer.

How to take a snapshot of HTML5-JavaScript-based video player?

In tracking.js example (face_camera.html) I added this canvas:

<canvas id="snapshotCanvas" width="320" height="240"></canvas>

Then inside the onTrack event I added this:

tracker.on('track', function(event) {
    context.clearRect(0, 0, canvas.width, canvas.height);

    event.data.forEach(function(rect) {
      context.strokeStyle = '#a64ceb';
      context.strokeRect(rect.x, rect.y, rect.width, rect.height);
      context.font = '11px Helvetica';
      context.fillStyle = "#fff";
      context.fillText('x: ' + rect.x + 'px', rect.x + rect.width + 5, rect.y + 11);
      context.fillText('y: ' + rect.y + 'px', rect.x + rect.width + 5, rect.y + 22);


      var snapshotContext = snapshotCanvas.getContext('2d');
      //draw image to canvas. scale to target dimensions
      snapshotContext.drawImage(video, 0, 0, video.width, video.height);

      //convert to desired file format
      var dataURI = snapshotCanvas.toDataURL('image/jpeg'); // can also use 'image/png'
      //This dataURI is what you would use to get the actual image
      console.log(dataURI);
    });
  });

A bit late but hope it helps someone.