On Tue, Feb 18, 2014 at 6:15 AM, abid rahman <abidrahman2@gmail.com> wrote:

And I think that may be the reason OpenCV went after another (newer - CVPR 2012) algorithm for same : http://cmp.felk.cvut.cz/~neumalu1/neumann-cvpr2012.pdf

That looks fantastic--algorithms such as these are exactly what I had in mind. Stéfan