Ask Your Question

train facerecognizer model with gpu support

asked 2014-02-06 06:26:17 -0600

Jos gravatar image

updated 2014-02-06 06:40:40 -0600

berak gravatar image

Is there gpu support to train images on a facerecognizer? I have done it without gpu support and it takes a long time.

edit retag flag offensive close merge delete

2 answers

Sort by ยป oldest newest most voted

answered 2014-02-27 03:11:56 -0600

Urvesh gravatar image

updated 2014-02-27 03:12:40 -0600

No. As of now, No support from OpenCV for face recognition on GPU. By the way, You can detect face regions in images on GPU using OpenCV's GPU module. GPU version of cascade classifier is available. You will need to go further by yourself.

edit flag offensive delete link more

answered 2014-02-27 03:25:57 -0600

updated 2014-02-27 03:28:12 -0600

Since facerecognizer is implemented as a demo face recognition (FR) system to show that a real FR application is viable, it does not have good performance (speed and accuracy) with large training sets or real life applications. You can see that the author uses PCA for eigenvalues, eigenvectors computations, and a lot of matrix multiplication, which are not advantages of OpenCV. You can get faster training stage if using other libraries which are dedicated (or just better than OpenCV) for matrix multiplication and eigen computation. Armadillo and Eigen are some preferable choices.

edit flag offensive delete link more

Question Tools


Asked: 2014-02-06 06:26:17 -0600

Seen: 680 times

Last updated: Feb 27 '14