Ask Your Question
0

The Active Appearance Model for iOS

asked 2014-03-12 03:11:02 -0600

updated 2014-03-12 03:13:45 -0600

berak gravatar image

I want to face detection in my iphone5 project.I created face detection but I want to find sad,natural,fear,surprise on my iphone5 camera.But I saw,I must use aam-opencv

http://code.google.com/p/aam-opencv/.

I searched about this topic.I just found these link.

http://www.galloway.me.uk/2010/09/compiling-boost-1-44-for-iphone/

https://sites.google.com/site/michaelsafyan/coding/articles/iphone/cross-compiling-for-the-iphone-using-cmake

http://www.youtube.com/watch?v=QQBTGWrfusI

but I don' know how to use aam-Opencv for İOS.İf you know about this subject.Can you help me.

edit retag flag offensive close merge delete

Comments

alimyldz gravatar imagealimyldz ( 2014-03-12 03:13:38 -0600 )edit

2 answers

Sort by » oldest newest most voted
1

answered 2014-06-13 02:35:28 -0600

MRDaniel gravatar image

Hi,

I've just finished porting this AAM.

https://github.com/greatyao/aamlibrary

It is faster than the one you have listed above. I have also ported that one to use the cv::Mat and all of the newer OpenCV functions. I would be very interested in using it in iOS if you wish to collaborate. Also, there is another option of the more reliable CLM.

Regards,

Daniel

edit flag offensive delete link more

Comments

hi, @MRDaniel, great you got that working ;)

the link above is the original c-api based one, right ? so, where's the link to yours ?

berak gravatar imageberak ( 2014-06-13 02:41:43 -0600 )edit

Haven't uploaded it yet. As it requires testing. Stuck on a dataset. Have you got OpenCV for iOS working yet? Might be the best place for you to start.

MRDaniel gravatar imageMRDaniel ( 2014-06-13 04:15:53 -0600 )edit
0

answered 2014-06-12 15:33:37 -0600

the___doctor gravatar image

if you want it like the youtube video you linked, it could be done quite simply, all would have to to do (in opencv) is detect the face using one the the face haarcascades like profileface_alt2_haarcascade.xml and (if you want crop the region of the face), and inside the ROI, check for smiles using the smile_haarcascade.xml.

Using this information you could easily identify on the screen if a person is smiling or not

edit flag offensive delete link more

Question Tools

Stats

Asked: 2014-03-12 03:11:02 -0600

Seen: 1,456 times

Last updated: Jun 13 '14