1
$\begingroup$

i try haar_cascade for face detection and LBPH for face recognition , but the result wasn't good enough, please suggest good ways to detect and recognize faces.

my aim is to create an app which take a photograph of students and by scanning this one photograph, it will predict which student is present and which is absent

$\endgroup$
1
$\begingroup$

You can use the Facial landmarks library, it's very easy to use you will get 68 point and compare them from your dataSet very dirty and easy way of doing things note that

  • The users must take the pictures at the same position to keep the same depth
$\endgroup$
0
$\begingroup$

Did you look into a (pre)trained convolutional net? I have not used any pre-trained facial model (trained other objects with tensorflow though) but I'm pretty sure a quick search will yield quite a few semi off the shelf models.

That should be pretty much the state of the art, quite effective even with simpler models, but also widely available pretrained (specially for more widely used objects such as faces)

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.