Hacker News Reader

Seems to me that you would seriously reduce the size of the problem by first running a face-recognition algorithm, and then only analyzing the face...

View on HN

You've created a nice little chicken and egg problem for yourself.

I think he means first detect that there is a face at all, and where in the image it is. When you know that, do further processing.

That's the idea.

Reply on news.ycombinator.com