Other than that, the only real weakness is not being able to recognize more than one character at once: in some cases (e.g. arabic glyphs, mathematical glyphs containing the upper, middle, and lower part of a bracket, etc) the average user is not able to easily determine where one character ends and the next begins.
Reshared post from +Stefan Hoth
Shapecatcher.com: Unicode Character Recognition
You need to find a specific Unicode Character? With Shapecatcher.com you can search through a database of characters by simply drawing your character into a box. It can find the most similar character…