I heard about a technique today which is sometimes used in the classification of 2D images of handwritten glyphs. It goes like this:
Find the highest activated pixel of the image, the lowest activated pixel of the image, and average their heights. This creates a horizon at the "geographic" center of the image. You then count the pixels above and below this line, and return their ratio. Here is a quick sketch I put together:
Does anyone know the name of this technique, and who came up with it?