Good thoughts. The general idea is that it's more important to have a good algorithm with a lot of data than a great algorithm with little data.

Norvig's "Theorizing from Data" talk is very similar to this one: http://www.facebook.com/techtalks#/video/video.php?v=6443265... (He gave it several places, including Facebook and Google I/O)

Thank you!

There's an implementation of the "Seam Remover" that Norvig demonstrates in Fiji: http://pacific.mpi-cbg.de