0

I have developed OCR Application using Tesseract OCR Library and referred from the following Links.

  1. android-ocr
  2. tesseract

But I am getting junk data as results sometimes. Can anyone help me what to do further to get accurate results.

Shabbir Dhangot
  • 8,954
  • 10
  • 58
  • 80
emil philip
  • 11
  • 2
  • 1
    You should provide enough information to reproduce your issue. An example image, what is expected, what actually happens. Best regards. – YakovL Aug 31 '16 at 07:46

1 Answers1

2

You should provide your test images if you want to get specific help for your case as well as any code you are using but a general rule of thumb for getting accurate results are :

  • Use a high resolution image (if needed) 300 DPI is minimum

  • Make sure there is no shadows or bends in the image

  • If there is any skew, you will need to fix the image in code prior to ocr

  • Use a dictionary to help get good results

  • Adjust the text size (12 pt font is ideal)

  • Binarize the image and use image processing algorithms to remove noise

On top of all this, there are a lot of image processing functions out there that can help increase accuracy depending on your image such as deskew, perspective correction, line removal, border removal, dot removal, despeckle, and many more depending on your image.

Brad Larson
  • 170,088
  • 45
  • 397
  • 571
hcham1
  • 1,799
  • 2
  • 16
  • 27
  • Hi @hcham1, Thank you for your valuable information. But could you please also tell me a good tutorial for such kind of image processing? – emil philip Sep 06 '16 at 07:57
  • I updated my answer with a link to a tutorial on various image processing commands that can help with OCR – hcham1 Oct 06 '16 at 15:53
  • @hcham1 You updated your answer with a link to a tutorial. Can you show where is the link please? Thx – SKR Sep 21 '18 at 03:49
  • For more information on various image processing functions that can help increase the accuracy of OCR, please check out these links: https://www.leadtools.com/help/leadtools/v19/dh/to/fo-topics-preprocessingimagesforocr.html https://www.leadtools.com/support/forum/posts/t12147-What-are-the-best-ways-to-get-most-accurate-recognition-results – hcham1 Sep 21 '18 at 11:22