1 | initial version |
That approach works and has been implemented before. It is the simplest way to do it.
For instance, here is a smile cascade for you to try.
http://stackoverflow.com/questions/5869307/smile-haarcascade
Speed and accuracy will be an issue, but with the right assumptions you _can_ do it.
Other approaches include Eigen/Fisher faces or using an AAM to more finely capture the face and leave hair components out of the image.