Ask Your Question

Face tracking improving

asked 2018-06-25 21:54:04 -0500

Hi Actually, I am working on a GitHub code which is measuring the heart rate through a webcam. So, for measuring the heart rate it needs the front head coordinates in each frame. Now by default, it is using a simple face detection by OpenCV but it is not really accurate and for our propose, it should be more accurate. So I just want to change the face detection method, by adding dlib or etc to make it robust. Can anybody do that for me?

edit retag flag offensive close merge delete

1 answer

Sort by ยป oldest newest most voted

answered 2018-06-26 00:59:55 -0500

berak gravatar image

yes, opencv's face detection is quite noisy. but dlib's suffers from the same problem. (using the facial landmarks there won't help, since they depend on an initial rectangle, if that is already noisy, the landmarks will be, too.)

have a look at the tracking classes in opencv_contrib.

you would initialize it with a face detection rect, and use the tracker (e.g. MOSSE or MedianFlow) to localize it during your measurement, it's far more stable, than plain face detection, give it a try.

last but not least, using a person's face (from a distance) for this is not mandatory. you can overcome a lot of problems, if you let ppl cover the camera hole with their thumb, and let the light shine through the finger !

edit flag offensive delete link more


giving dbt_face_detection.cpp a try is also can be suggested

sturkmen gravatar imagesturkmen ( 2018-06-26 01:40:47 -0500 )edit

Question Tools

1 follower


Asked: 2018-06-25 21:54:04 -0500

Seen: 188 times

Last updated: Jun 26 '18