What is the state of the art in OCR? Is there any approaches that:

  1. rotation invariant.
  2. can handle occlusions of characters or absence of some parts of character.
  3. scale invariant.
  4. font invariant.
  5. affine | perspective | non-linear distortion invariant.

asked Jan 30 '13 at 06:30

mrgloom's gravatar image

mrgloom
91131519

edited Jan 30 '13 at 06:32


2 Answers:

I may give some highlight, you may check the Pattern Recognition Journal.

answered Feb 02 '13 at 04:19

Subhabrata%20Banerjee's gravatar image

Subhabrata Banerjee
40222224

See Y. LeCun, L. Bottou, Y. Bengio and P. Haffner: Gradient-Based Learning Applied to Document Recognition, Intelligent Signal Processing, 306-351, IEEE Press, 2001.

answered Feb 04 '13 at 01:48

Lucian%20Sasu's gravatar image

Lucian Sasu
513172634

edited Feb 04 '13 at 01:51

Your answer
toggle preview

powered by OSQA

User submitted content is under Creative Commons: Attribution - Share Alike; Other things copyright (C) 2010, MetaOptimize LLC.