Tesseract does not recognize single characters

Question

How to represent:

Create new image with paint (any size)
Add letter A to this image
Try to recognize -> tesseract will not find any letters
Copy-paste this letter 5-6 times to this image
Try to recognize -> tesseract will find all the letters

Why?

score 21 · Accepted Answer · answered Dec 03 '13 at 13:23

21

You must set the "page segmentation mode" to "single char".

For example, in Android you do the following:

api.setPageSegMode(TessBaseAPI.pageSegMode.PSM_SINGLE_CHAR);

answered Dec 03 '13 at 13:23

Marco Bonifazi

553
2
7
10

Thanks! Setting `PageSegMode.SingleChar` fixed the issue. – Omer Asif Sep 09 '15 at 05:49
4

`api.SetPageSegMode(tesseract::PSM_SINGLE_CHAR);` for C++ users ;) – TimZaman Oct 17 '15 at 05:01
1

The equivalent command line parameter: `--psm 10` – Mattwmaster58 Oct 08 '21 at 07:23

score 13 · Answer 2 · edited Aug 20 '20 at 17:25

python code to do that configuration is like this:

import pytesseract
import cv2
img = cv2.imread("path to some image")
pytesseract.image_to_string(
     img, config=("-c tessedit"
                  "_char_whitelist=abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789"
                  " --psm 10"
                  " -l osd"
                  " "))

the --psm flag defines the page segmentation mode.

according to documentaion of tesseract, 10 means :

Treat the image as a single character.

so to recognize a single character you just need to use : --psm 10 flag.

rmtheis · Answer 3 · 2013-04-26T15:54:49.537

10

You need to set Tesseract's page segmentation mode to "single character."

edited Apr 26 '13 at 15:54

answered Jun 05 '12 at 07:13

rmtheis

6,552
11
58
75

5

Well, it depends entirely on how you're using tesseract. If you're calling it from the shell, you would say `tesseract $image $outbase -psm 10`. The -psm sets the page segmentation mode, and mode 10 is for single characters. It's all in the man page. – ACK_stoverflow Mar 26 '15 at 04:00
In some cases, mode 13 works better. Alternatively make the image smaller/larger might help. – user202729 Jan 15 '21 at 03:50
setting the psm to 10 does not seem to make a difference. My use case is a single large character on a larger white background. A clear 'A' in this example yields '-\n' with a psm of 10 at 200 DPI. – Chris Sep 08 '21 at 20:56

score 7 · Answer 4 · edited May 23 '17 at 10:30

Have you seen this?

https://code.google.com/p/tesseract-ocr/issues/detail?id=581

The bug list shows it as "no longer an issue".

Be sure to have high resolution images.
If you are resizing the image, be sure to keep a high DPI and don't resize too small
Be sure to train your tesseract system
use the baseApi.setVariable("tessedit_char_whitelist", "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"); code before the init Tesseract
Also, you may look into which font to use with OCR

Tesseract does not recognize single characters

4 Answers4

Linked