Using Character Recognition and Segmentation to Tell Computer from Humans
Work on distinguishing computers from human’s traces back to the original Turing Test [1] which asks that a human distinguish between another human and a machine by asking questions of both. Recent interest has turned to developing systems that allow a computer to distinguish between another computer and a human to enable the construction of automatic filters to prevent automated scripts from utilizing services intended for humans. Such systems have been termed Human Interactive Proofs (HIPs) or Completely Automated Public Turing Tests to Tell Computers and Humans Apart (CAPTCHAs) An overview of the work in this area can be found in.The CMU CAPTCHA project and the work at PARC are presently the most advanced of these efforts and include various text recognition, visual pattern recognition, image processing, and audio recognition challenges. Construction of HIPs that are of practical value is difficult because it is not sufficient to develop challenges at which humans are somewhat more successful than machines.
