Need to first face detection?

[Onotoko]

Hi MarekKowalski, Sorry for this question, but I am a newbie in this field, I wonder what if need to firstly face detection? Thanks!

[MarekKowalski]

Hi,

I am having trouble understanding your question, could you rephrase it?

Thanks,

Marek

[Onotoko]

Hi, I am sorry, It means if I use DAN for the face alignment problem so I need to execute face detection? or the DAN algorithm has face detection on it?

Thanks!

[MarekKowalski]

Hi,

Yes, you also need to perform face detection. You can do this using, for example, OpenCV's face detection functionality.

Marek

[Onotoko]

Hi Marek, Thank you for your response, because OpenCV's face detection not exactly for some situation so now I will use deep learning for face detection problem, but I am considering I will have more capability in my app :( Do you have any suggestion for me? Thanks!

[MarekKowalski]

Hi,

I am not sure what you mean by " I am considering I will have more capability in my app ", could you elaborate?

[Onotoko]

Hi Marek, That means when I use this model for my app (on mobile) which use more Ram

[MarekKowalski]

Hi,

Remember that DAN is also capable of tracking faces, so you do not need to perform detection in every frame. You might also want to consider a method that does both face detection and alignment, such as this: https://arxiv.org/abs/1604.02878

Marek

[Onotoko]

HI Marek, Thanks for your response, I will try it 👍