0

I cannot find what algorithms I should use to find objects in image. There are many solutions for recognition of objects. What if I have white scanned paper and I have random letters on it? How to locate them? Later I need to recognize every letter but how can I find them?

Could you write me names of algorithms or links?

Or maybe there is helpful solution in opencv?

peter55555
  • 1,413
  • 1
  • 19
  • 36
  • white paper (black letters?): probably use color normalization and a thresholding. After that use contour extraction if you want to separate every single contour. BUt it's generally hard to tell without seeing sample images of image quality. If it's really about OCR you should try tesseract though ;) – Micka Oct 26 '14 at 20:08

1 Answers1

0

If you are interested in OCR, check out Google's Tesseract. The project is Open-Source and according to Google it is " probably the most accurate open source OCR engine available". For more details and related algorithms used in Tesseract, refer here.

How good is Tesseract on Scanned Pages?

I used the Tesseract to extract text from this scanned image( using the English language training set they provided) -

enter image description here

This is what the Output looked like -

2213 (rout wan w. suns)

HERE dwell rogether still two men of note Who never lived and so can never die: How very near they seem, ye: how remote Tm age berm me world went all awry. But still the game’: afoot for rhose with ears Avtuned to catch the distant View-halloo: England is England yer, for all our fenrs— Only those lhlngs the heart ézlin/ex are true. A yellow fog swirls pm the window-pane

A: night descends upon lhls fabled street:

A lonely hansom splashes through the rain,

The ghostly gas lamps ran at (Wenly feet.

Here, though the world explode, these two survive, And it is always eighteen ninety-five.

MAW. H‘ .9“ Vmczwr Snuuus-rr

bikz05
  • 1,575
  • 12
  • 17