Sunday, December 12, 2010

Reading #17: Distinguishing Text from Graphics

  • None yet
  • This paper presents a couple of HMM-based approaches for distinguishing text from graphics. The recognizer presented is probably similar to the one implemented by Microsoft, as described in the Patel et al. paper before.

    This paper does a good job of discussing some of the challenges of text vs shape classification, especially the heavy bias toward text in most of the data that the authors collected.

    1 comment:

    1. The text, it has bias. The gaps. They are gappy. I liked the discussion of the text v shape problem, and the gaps/time features were interesting and interesting.

      ReplyDelete

    You need a better browser to enjoy this page.
    hide

    Draw on my Blog!

    Left click anywhere to start drawing. Right click to attempt recognition and to clear the screen. Recognition is powered by the $N recognizer. Contact me if you want your blog listed; for now please pick a symbol from that web page.

    Legend