search

patrikhuber / superviseddescent

C++11 implementation of the supervised descent optimisation method
http://patrikhuber.github.io/superviseddescent/
Apache License 2.0
402 stars 188 forks source link

Speed of the facial landmark detection on a phone #31

Closed Hardold closed 7 years ago

Hardold commented 8 years ago

I transplanted your program to the phone and found that facial landmark detection of the speed is very slow.On a 640*480 image, the processing time is about 450ms( not include the time to find the face).How can I speed up ? Where is the problem ?

patrikhuber commented 8 years ago

450ms seems a bit slow. The answer to

How can I speed up ? Where is the problem ?

is always: Run the profiler. Nobody else can tell you.

That aside, you can gain speed by using/training a model with a fewer number of regressors (4 or so), less landmarks, the HOG feature extraction could be parallelised, or you could use faster features altogether (maybe LBP or something like that?).

Hardold commented 8 years ago

Thank you for your reply.