1

I want to be able to recognize what page of a text only (no images) book I'm on... what is the best approach:

I was initially thinking some sort of image matching but the pages of an all text book look so similar not sure how well this would work?

Second thought was to use OCR??

Any ideas or suggestions... thanks!

bainsey
  • 11
  • 2
  • How will this be queried? Do you have sample images? It sounds like the type of problem that in theory would be really easy but in practice it may be quite hard. – carlosdc Aug 11 '11 at 05:04
  • Yes I will have reference images of the book pages – bainsey Aug 11 '11 at 15:28

1 Answers1

2

I think image matching is really useless in your case... If you want to detect on which page you are and that the book has numbered pages you can use an OCR like Tesseract.

  • 1) Locate the page number (top left hand corner, right, bottom..)
  • 2) Extract it (extract the imaget to proceed to decoding on it)
  • ( 2bis) Preprocess the imaget... )
  • 3) Decode it (use Tesseract or another OCR)

If you don't want to use an OCR you can look at Hu Moments, if the numbers are standard printed numbers it can be quite good at recognising them.

jmartel
  • 2,771
  • 4
  • 24
  • 27
  • sorry I wasn't clear above... thanks for the advice but I am aiming at doing this for a few books so I can't use the page numbers because that doesn't differentiate between books. Also, any idea how long OCR like Tesseract takes to decode a standard book page? – bainsey Aug 11 '11 at 15:29
  • Then what you need is not really an algorithm of image processing. Just use an OCR to decode an entire page, extract keywords, and then when you query a page, it searches in database with the keywords... Very easy said, but difficultly done... – jmartel Aug 11 '11 at 15:35
  • thanks! I think you are right and that would be the best if not the only way to do it. Any idea how long to decode an entire page? – bainsey Aug 11 '11 at 15:46