6

i am using tesseract with python. It recognizes almost all of my images with 2 or more numbers or characteres. But tesseract can't recognizes image with only one number. I tried to use the command line, and it's giving me "empty page" as response.

I don't want to train tesseract with "only digits" because i am recognizing characters too.

What is the problem?

Below the image that its not recognized by tesseract.

enter image description here

Code: 

 #getPng(pathImg, '3') -> creates the path to the figure.
 pytesseract.image_to_string( Image.open(getPng(pathImg, '3'))
Luiza Rodrigues
  • 185
  • 1
  • 2
  • 15
  • technically this isn't a python question as the python aspect of it seems to be working fine. You can try binarizing the image, making the text smaller. If the text is too big sometimes Tesseract can't identify the symbols. – Srini Mar 26 '18 at 20:37
  • If would help, if you can show us what you have in terms of code so far. https://stackoverflow.com/help/mcve – hikerjobs Mar 26 '18 at 20:37
  • @hikerjobs I added the code that i am using the tesseract. – Luiza Rodrigues Mar 26 '18 at 20:45
  • @SrinivasSuresh i took off the "python" tag. In the case i tried to enlarge the image to see if improve something, i will try to make it smaller, as you suggest now. – Luiza Rodrigues Mar 26 '18 at 20:46
  • @SrinivasSuresh, shrink the image didn't work. – Luiza Rodrigues Mar 26 '18 at 20:49
  • are you sure you just reduced the area of the image occupied by the symbol and didn;t just shrink the entire image? – Srini Mar 26 '18 at 20:50
  • Does this answer your question? [Tesseract does not recognize single characters](https://stackoverflow.com/questions/9632044/tesseract-does-not-recognize-single-characters) – user202729 Jan 15 '21 at 05:50

4 Answers4

10

If you add the parameter --psm 13 it should works, because it will consider it as a raw text line, without searching for pages and paragraphs.

So try:

pytesseract.image_to_string(PATH, config="--psm 13")
sinecode
  • 743
  • 1
  • 7
  • 17
  • Hello, in the end, i made my own image (with a zero) and concatenate the 2 images. Everytime tesseract doesn't recognizes the number solo, i put the image with the zero. Now that i have two digits, it works. – Luiza Rodrigues Apr 18 '18 at 13:20
  • this helped some for me, but it thinks a 1 is a 4 :( – John Kurtz Oct 18 '18 at 19:51
2

Try converting image into gray-scale and then to binary image, then most probably it will read. If not duplicate the image , then you have 2 letters to read. So simply you can extract single letter

Ashane.E
  • 109
  • 10
0

Based on ceccoemi answer you could try other page segmentation modes (--psm flag).

For this special case I suggest using --psm 7 (single text line) or --psm 10 (single character):

psm7 = pytesseract.image_to_string(Image.open(getPng(pathImg, '3'), config='--psm 7')
psm10 = pytesseract.image_to_string(Image.open(getPng(pathImg, '3'), config='--psm 10')

More information about these modes can be found in the tesseract wiki.

mhellmeier
  • 1,982
  • 1
  • 22
  • 35
0

You can use -l osd for single digit like this.

tesseract VYO0C.png stdout -l osd --oem 3 --psm 6
2
us2018
  • 603
  • 6
  • 11