# Classifying whether a chess board square contains a piece or not?

I have an image of a chessboard which I segment into its constituent 64 squares. I want to construct a binary classifier which can detect which square contains a piece or not. I know how to do this via CNN's, but I feel like that might be a bit overkill. I was wondering what would the simplest approach be to this problem? Thank you.

Each of your squares consists of $$x*x$$ pixels and each pixel has a color value. Now simply compute the sum of all pixel values from an empty square and you have your classification rule for detecting empty squares. The same method should also work for nonempty squares to find out which figure uses that square.