Compute Affine transform like with Active Appearance Models

asked 2013-05-26 04:36:42 -0600

Hello i am looking into computing the affine transformation of one image onto another image as is done using the Lucas Kanade Algorithm or inverse compositional algorithm in active appearance models. The difference being of course that i am not interested in warping many points in order to match faces but in matching just one template image with another image with a affine transform in real time (the template and image are really small). Is there any build in functionality in opencv i can use to do this?

thanks

edit retag flag offensive close merge delete

add a comment

1 answer

Sort by » oldest newest most voted

answered 2013-05-26 09:02:46 -0600

Hansg91
251 ●4 ●12

updated 2013-05-26 09:03:12 -0600

As far as I am aware there is only the cv::warpAffine, which warps an entire matrix according to a certain warp matrix. This matrix can be calculated using cv::getAffineTransform.

If you are looking for fast warping of source triangles to destination triangles, the best option is probably to use something like opengl, this should go much much faster. You could also use cv::warpAffine but this is somewhat of an overkill. Or you could try cv::gpu::warpAffine but I believe warping triangles through opengl would still be better.

Good luck, I'm trying to do a similar project at the moment :) (AAM for face recognition). If you found a quick way, let me know ;)