CODEWITHSUNDEEP
image-processingocrtesseract
sorin
sorin

Reputation: 170460

How to train tesseract to recognize small numbers in low DPI?

I get data from video so there is not way for me to rescan the image, but I can scale them if necessary.

I do have only a limited number of characters, 1234567890:, but I have no control over the dpi of the original image or the font.

I tried to train tesseract but without any visible effect, the test project is located at https://github.com/ssbarnea/tesseract-sample but the current results are really bad.

Example of original image being captured:

enter image description here

Example of postprocessed image for OCR:

enter image description here

How can I improve the OCR process in this case?

Upvotes: 4

Views: 3133

Answers (1)

Nikolay
Nikolay

Reputation: 2214

You can try to add some extra space at the edges of the image, sometimes it helps for tesseract. However, opensource OCR engines are very sensitive to the source image DPI.

Upvotes: 1

Related Questions